Search

We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians to produce accurate and realistic strand-based reconstructions from multi-view data. In contrast to recent approaches that leverage unstructured Gaussians to model human avatars, our method reconstructs the hair using 3D polylines, or strands. This fundamental difference allows the use of the resulting hairstyles out-of-the-box in modern computer graphics engines for editing, rendering, and simulation. Our 3D lifting method relies on unstructured Gaussians to generate multi-view ground truth data to supervise the fitting of hair strands. The hairstyle itself is represented in the form of the so-called strand-aligned 3D Gaussians. This representation allows us to combine strand-based hair priors, which are essential for realistic modeling of the inner structure of hairstyles, with the differentiable rendering capabilities of 3D Gaussian Splatting. Our method, named Gaussian Haircut, is evaluated on synthetic and real scenes and demonstrates state-of-the-art performance in the task of strand-based hair reconstruction.

We introduce Gaussian Garments, a novel approach for reconstructing realistic simulation-ready garment assets from multi-view videos. Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color and high-frequency surface details. This representation enables accurate registration of garment geometries to multi-view videos and helps disentangle albedo textures from lighting effects. Furthermore, we demonstrate how a pre-trained graph neural network (GNN) can be fine-tuned to replicate the real behavior of each garment. The reconstructed Gaussian Garments can be automatically combined into multi-garment outfits and animated with the fine-tuned GNN.

Generating realistic human motion is essential for many computer vision and graphics applications. The wide variety of human body shapes and sizes greatly impacts how people move. However, most existing motion models ignore these differences, relying on a standardized, average body. This leads to uniform motion across different body types, where movements don't match their physical characteristics, limiting diversity. To solve this, we introduce a new approach to develop a generative motion model based on body shape. We show that it's possible to train this model using unpaired data by applying cycle consistency, intuitive physics, and stability constraints, which capture the relationship between identity and movement. The resulting model generates diverse, physically plausible, and dynamically stable human motions that are both quantitatively and qualitatively more realistic than current state-of-the-art methods. More details are available on our project page https://CarstenEpic.github.io/humos/., Comment: Accepted in ECCV'24. Project page: https://CarstenEpic.github.io/humos/

Against the backdrop of enthusiasm for large language models (LLMs), there is an urgent need to scientifically assess their capabilities and shortcomings. This is nontrivial in part because it is difficult to find tasks which the models have not encountered during training. Utilizing symbolic graphics programs, we propose a domain well-suited to test multiple spatial-semantic reasoning skills of LLMs. Popular in computer graphics, these programs procedurally generate visual data. While LLMs exhibit impressive skills in general program synthesis and analysis, symbolic graphics programs offer a new layer of evaluation: they allow us to test an LLM's ability to answer different-grained semantic-level questions of the images or 3D geometries without a vision encoder. To semantically understand the symbolic programs, LLMs would need to possess the ability to "imagine" and reason how the corresponding graphics content would look with only the symbolic description. We use this task to evaluate LLMs by creating a large benchmark for the semantic visual understanding of symbolic graphics programs, built procedurally with minimal human effort. Particular emphasis is placed on transformations of images that leave the image level semantics invariant while introducing significant changes to the underlying program. We evaluate commercial and open-source LLMs on our benchmark to assess their ability to reason about visual output of programs, finding that LLMs considered stronger at reasoning generally perform better. Lastly, we introduce a novel method to improve this ability -- Symbolic Instruction Tuning (SIT), in which the LLM is finetuned with pre-collected instruction data on symbolic graphics programs. Interestingly, we find that SIT not only improves LLM's understanding on symbolic programs, but it also improves general reasoning ability on various other benchmarks., Comment: Technical Report v2 (46 pages, 24 figures, project page: https://sgp-bench.github.io/, substantial update from v1)

The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The key challenges include the scarcity of training data and the need to design a model that accurately edits the source motion. In this paper, we address both challenges. We propose a methodology to semi-automatically collect a dataset of triplets comprising (i) a source motion, (ii) a target motion, and (iii) an edit text, introducing the new MotionFix dataset. Access to this data allows us to train a conditional diffusion model, TMED, that takes both the source motion and the edit text as input. We develop several baselines to evaluate our model, comparing it against models trained solely on text-motion pair datasets, and demonstrate the superior performance of our model trained on triplets. We also introduce new retrieval-based metrics for motion editing, establishing a benchmark on the evaluation set of MotionFix. Our results are promising, paving the way for further research in fine-grained motion generation. Code, models, and data are available at https://motionfix.is.tue.mpg.de/ ., Comment: SIGGRAPH Asia 2024 Camera Ready, Project page: https://motionfix.is.tue.mpg.de

Pose estimation has promised to impact healthcare by enabling more practical methods to quantify nuances of human movement and biomechanics. However, despite the inherent connection between pose estimation and biomechanics, these disciplines have largely remained disparate. For example, most current pose estimation benchmarks use metrics such as Mean Per Joint Position Error, Percentage of Correct Keypoints, or mean Average Precision to assess performance, without quantifying kinematic and physiological correctness - key aspects for biomechanics. To alleviate this challenge, we develop OpenCapBench to offer an easy-to-use unified benchmark to assess common tasks in human pose estimation, evaluated under physiological constraints. OpenCapBench computes consistent kinematic metrics through joints angles provided by an open-source musculoskeletal modeling software (OpenSim). Through OpenCapBench, we demonstrate that current pose estimation models use keypoints that are too sparse for accurate biomechanics analysis. To mitigate this challenge, we introduce SynthPose, a new approach that enables finetuning of pre-trained 2D human pose models to predict an arbitrarily denser set of keypoints for accurate kinematic analysis through the use of synthetic data. Incorporating such finetuning on synthetic data of prior models leads to twofold reduced joint angle errors. Moreover, OpenCapBench allows users to benchmark their own developed models on our clinically relevant cohort. Overall, OpenCapBench bridges the computer vision and biomechanics communities, aiming to drive simultaneous advances in both areas.

Reinforcement Learning has achieved significant success in generating complex behavior but often requires extensive reward function engineering. Adversarial variants of Imitation Learning and Inverse Reinforcement Learning offer an alternative by learning policies from expert demonstrations via a discriminator. However, these methods struggle in complex tasks where randomly sampling expert-like behaviors is challenging. This limitation stems from their reliance on policy-agnostic discriminators, which provide insufficient guidance for agent improvement, especially as task complexity increases and expert behavior becomes more distinct. We introduce RILe (Reinforced Imitation Learning environment), a novel trainer-student system that learns a dynamic reward function based on the student's performance and alignment with expert demonstrations. In RILe, the student learns an action policy while the trainer, using reinforcement learning, continuously updates itself via the discriminator's feedback to optimize the alignment between the student and the expert. The trainer optimizes for long-term cumulative rewards from the discriminator, enabling it to provide nuanced feedback that accounts for the complexity of the task and the student's current capabilities. This approach allows for greater exploration of agent actions by providing graduated feedback rather than binary expert/non-expert classifications. By reducing dependence on policy-agnostic discriminators, RILe enables better performance in complex settings where traditional methods falter, outperforming existing methods by 2x in complex simulated robot-locomotion tasks.

Generating personalized 3D avatars is crucial for AR/VR. However, recent text-to-3D methods that generate avatars for celebrities or fictional characters, struggle with everyday people. Methods for faithful reconstruction typically require full-body images in controlled settings. What if a user could just upload their personal "OOTD" (Outfit Of The Day) photo collection and get a faithful avatar in return? The challenge is that such casual photo collections contain diverse poses, challenging viewpoints, cropped views, and occlusion (albeit with a consistent outfit, accessories and hairstyle). We address this novel "Album2Human" task by developing PuzzleAvatar, a novel model that generates a faithful 3D avatar (in a canonical pose) from a personal OOTD album, while bypassing the challenging estimation of body and camera pose. To this end, we fine-tune a foundational vision-language model (VLM) on such photos, encoding the appearance, identity, garments, hairstyles, and accessories of a person into (separate) learned tokens and instilling these cues into the VLM. In effect, we exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar. Importantly, we can customize avatars by simply inter-changing tokens. As a benchmark for this new task, we collect a new dataset, called PuzzleIOI, with 41 subjects in a total of nearly 1K OOTD configurations, in challenging partial photos with paired ground-truth 3D bodies. Evaluation shows that PuzzleAvatar not only has high reconstruction accuracy, outperforming TeCH and MVDreamBooth, but also a unique scalability to album photos, and strong robustness. Our code and data are publicly available for research purpose at https://puzzleavatar.is.tue.mpg.de/, Comment: Page: https://puzzleavatar.is.tue.mpg.de/, Code: https://github.com/YuliangXiu/PuzzleAvatar, Video: https://youtu.be/0hpXH2tVPk4

Learning-based approaches to cloth simulation have started to show their potential in recent years. However, handling collisions and intersections in neural simulations remains a largely unsolved problem. In this work, we present \moniker{}, a learning-based solution for handling intersections in neural cloth simulations. Unlike conventional approaches that critically rely on intersection-free inputs, \moniker{} robustly recovers from intersections introduced through missed collisions, self-penetrating bodies, or errors in manually designed multi-layer outfits. The technical core of \moniker{} is a novel intersection contour loss that penalizes interpenetrations and encourages rapid resolution thereof. We integrate our intersection loss with a collision-avoiding repulsion objective into a neural cloth simulation method based on graph neural networks (GNNs). We demonstrate our method's ability across a challenging set of diverse multi-layer outfits under dynamic human motions. Our extensive analysis indicates that \moniker{} significantly improves collision handling for learned simulation and produces visually compelling results., Comment: Accepted for publication by SIGGRAPH 2024, conference track

Numerous methods have been proposed to detect, estimate, and analyze properties of people in images, including the estimation of 3D pose, shape, contact, human-object interaction, emotion, and more. Each of these methods works in isolation instead of synergistically. Here we address this problem and build a language-driven human understanding system -- ChatHuman, which combines and integrates the skills of many different methods. To do so, we finetune a Large Language Model (LLM) to select and use a wide variety of existing tools in response to user inputs. In doing so, ChatHuman is able to combine information from multiple tools to solve problems more accurately than the individual tools themselves and to leverage tool output to improve its ability to reason about humans. The novel features of ChatHuman include leveraging academic publications to guide the application of 3D human-related tools, employing a retrieval-augmented generation model to generate in-context-learning examples for handling new tools, and discriminating and integrating tool results to enhance 3D human understanding. Our experiments show that ChatHuman outperforms existing models in both tool selection accuracy and performance across multiple 3D human-related tasks. ChatHuman is a step towards consolidating diverse methods for human analysis into a single, powerful, system for 3D human reasoning., Comment: Project page: https://chathuman.github.io

We address the problem of regressing 3D human pose and shape from a single image, with a focus on 3D accuracy. The current best methods leverage large datasets of 3D pseudo-ground-truth (p-GT) and 2D keypoints, leading to robust performance. With such methods, we observe a paradoxical decline in 3D pose accuracy with increasing 2D accuracy. This is caused by biases in the p-GT and the use of an approximate camera projection model. We quantify the error induced by current camera models and show that fitting 2D keypoints and p-GT accurately causes incorrect 3D poses. Our analysis defines the invalid distances within which minimizing 2D and p-GT losses is detrimental. We use this to formulate a new loss Threshold-Adaptive Loss Scaling (TALS) that penalizes gross 2D and p-GT losses but not smaller ones. With such a loss, there are many 3D poses that could equally explain the 2D evidence. To reduce this ambiguity we need a prior over valid human poses but such priors can introduce unwanted bias. To address this, we exploit a tokenized representation of human pose and reformulate the problem as token prediction. This restricts the estimated poses to the space of valid poses, effectively providing a uniform prior. Extensive experiments on the EMDB and 3DPW datasets show that our reformulated keypoint loss and tokenization allows us to train on in-the-wild data while improving 3D accuracy over the state-of-the-art. Our models and code are available for research at https://tokenhmr.is.tue.mpg.de., Comment: CVPR 2024

Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing methods (data-driven or using reinforcement learning) are limited in terms of generalization and motion naturalness. A primary obstacle is the scarcity of training data that combines locomotion with goal reaching. To address this, we introduce WANDR, a data-driven model that takes an avatar's initial pose and a goal's 3D position and generates natural human motions that place the end effector (wrist) on the goal location. To solve this, we introduce novel intention features that drive rich goal-oriented movement. Intention guides the agent to the goal, and interactively adapts the generation to novel situations without needing to define sub-goals or the entire motion path. Crucially, intention allows training on datasets that have goal-oriented motions as well as those that do not. WANDR is a conditional Variational Auto-Encoder (c-VAE), which we train using the AMASS and CIRCLE datasets. We evaluate our method extensively and demonstrate its ability to generate natural and long-term motions that reach 3D goals and generalize to unseen goal locations. Our models and code are available for research purposes at wandr.is.tue.mpg.de.

Inverse graphics -- the task of inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics. Successfully disentangling an image into its constituent elements, such as the shape, color, and material properties of the objects of the 3D scene that produced it, requires a comprehensive understanding of the environment. This complexity limits the ability of existing carefully engineered approaches to generalize across domains. Inspired by the zero-shot ability of large language models (LLMs) to generalize to novel contexts, we investigate the possibility of leveraging the broad world knowledge encoded in such models to solve inverse-graphics problems. To this end, we propose the Inverse-Graphics Large Language Model (IG-LLM), an inverse-graphics framework centered around an LLM, that autoregressively decodes a visual embedding into a structured, compositional 3D-scene representation. We incorporate a frozen pre-trained visual encoder and a continuous numeric head to enable end-to-end training. Through our investigation, we demonstrate the potential of LLMs to facilitate inverse graphics through next-token prediction, without the application of image-space supervision. Our analysis enables new possibilities for precise spatial reasoning about images that exploit the visual knowledge of LLMs. We release our code and data at https://ig-llm.is.tue.mpg.de/ to ensure the reproducibility of our investigation and to facilitate future research., Comment: TMLR camera-ready; 31 pages; project page: https://ig-llm.is.tue.mpg.de/

We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Previous text-to-motion methods focus on characters in isolation without considering scenes due to the limited availability of datasets that include motion, text descriptions, and interactive scenes. Our approach begins with pre-training a scene-agnostic text-to-motion diffusion model, emphasizing goal-reaching constraints on large-scale motion-capture datasets. We then enhance this model with a scene-aware component, fine-tuned using data augmented with detailed scene information, including ground plane and object shapes. To facilitate training, we embed annotated navigation and interaction motions within scenes. The proposed method produces realistic and diverse human-object interactions, such as navigation and sitting, in different scenes with various object shapes, orientations, initial body positions, and poses. Extensive experiments demonstrate that our approach surpasses prior techniques in terms of the plausibility of human-scene interactions, as well as the realism and variety of the generated motions. Code will be released upon publication of this work at https://research.nvidia.com/labs/toronto-ai/tesmo., Comment: Project Page: https://research.nvidia.com/labs/toronto-ai/tesmo/

Many classical parametric 3D shape models exist, but creating novel shapes with such models requires expert knowledge of their parameters. For example, imagine creating a specific type of tree using procedural graphics or a new kind of animal from a statistical shape model. Our key idea is to leverage language to control such existing models to produce novel shapes. This involves learning a mapping between the latent space of a vision-language model and the parameter space of the 3D model, which we do using a small set of shape and text pairs. Our hypothesis is that mapping from language to parameters allows us to generate parameters for objects that were never seen during training. If the mapping between language and parameters is sufficiently smooth, then interpolation or generalization in language should translate appropriately into novel 3D shapes. We test our approach with two very different types of parametric shape models (quadrupeds and arboreal trees). We use a learned statistical shape model of quadrupeds and show that we can use text to generate new animals not present during training. In particular, we demonstrate state-of-the-art shape estimation of 3D dogs. This work also constitutes the first language-driven method for generating 3D trees. Finally, embedding images in the CLIP latent space enables us to generate animals and trees directly from images.

We introduce bounded generation as a generalized task to control video generation to synthesize arbitrary camera and subject motion based only on a given start and end frame. Our objective is to fully leverage the inherent generalization capability of an image-to-video model without additional training or fine-tuning of the original model. This is achieved through the proposed new sampling strategy, which we call Time Reversal Fusion, that fuses the temporally forward and backward denoising paths conditioned on the start and end frame, respectively. The fused path results in a video that smoothly connects the two frames, generating inbetweening of faithful subject motion, novel views of static scenes, and seamless video looping when the two bounding frames are identical. We curate a diverse evaluation dataset of image pairs and compare against the closest existing methods. We find that Time Reversal Fusion outperforms related work on all subtasks, exhibiting the ability to generate complex motions and 3D-consistent views guided by bounded frames. See project page at https://time-reversal.github.io., Comment: project page at https://time-reversal.github.io

Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts. Our code and models are publicly available at https://mathis.petrovich.fr/stmc., Comment: CVPR 2024, HuMoGen Workshop

We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we first introduce BEAT2 (BEAT-SMPLX-FLAME), a new mesh-level holistic co-speech dataset. BEAT2 combines a MoShed SMPL-X body with FLAME head parameters and further refines the modeling of head, neck, and finger movements, offering a community-standardized, high-quality 3D motion captured dataset. EMAGE leverages masked body gesture priors during training to boost inference performance. It involves a Masked Audio Gesture Transformer, facilitating joint training on audio-to-gesture generation and masked gesture reconstruction to effectively encode audio and body gesture hints. Encoded body hints from masked gestures are then separately employed to generate facial and body movements. Moreover, EMAGE adaptively merges speech features from the audio's rhythm and content and utilizes four compositional VQ-VAEs to enhance the results' fidelity and diversity. Experiments demonstrate that EMAGE generates holistic gestures with state-of-the-art performance and is flexible in accepting predefined spatial-temporal gesture inputs, generating complete, audio-synchronized results. Our code and dataset are available https://pantomatrix.github.io/EMAGE/, Comment: Fix typos; Conflict of Interest Disclosure; CVPR Camera Ready; Project Page: https://pantomatrix.github.io/EMAGE/

Understanding how humans interact with the world necessitates accurate 3D hand pose estimation, a task complicated by the hand's high degree of articulation, frequent occlusions, self-occlusions, and rapid motions. While most existing methods rely on single-image inputs, videos have useful cues to address aforementioned issues. However, existing video-based 3D hand datasets are insufficient for training feedforward models to generalize to in-the-wild scenarios. On the other hand, we have access to large human motion capture datasets which also include hand motions, e.g. AMASS. Therefore, we develop a generative motion prior specific for hands, trained on the AMASS dataset which features diverse and high-quality hand motions. This motion prior is then employed for video-based 3D hand motion estimation following a latent optimization approach. Our integration of a robust motion prior significantly enhances performance, especially in occluded scenarios. It produces stable, temporally consistent results that surpass conventional single-frame methods. We demonstrate our method's efficacy via qualitative and quantitative evaluations on the HO3D and DexYCB datasets, with special emphasis on an occlusion-focused subset of HO3D. Code is available at https://hmp.is.tue.mpg.de

We present ESP, a novel method for context-aware full-body generation, that enables photo-realistic synthesis and inpainting of people wearing clothing that is semantically appropriate for the scene depicted in an input photograph. ESP is conditioned on a 2D pose and contextual cues that are extracted from the photograph of the scene and integrated into the generation process, where the clothing is modeled explicitly with human parsing masks (HPM). Generated HPMs are used as tight guiding masks for inpainting, such that no changes are made to the original background. Our models are trained on a dataset containing a set of in-the-wild photographs of people covering a wide range of different environments. The method is analyzed quantitatively and qualitatively, and we show that ESP outperforms the state-of-the-art on the task of contextual full-body generation., Comment: Accepted at ECCV 2024, Project: https://esp.is.tue.mpg.de

We present HAAR, a new strand-based generative model for 3D human hairstyles. Specifically, based on textual inputs, HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics engines. Current AI-based generative models take advantage of powerful 2D priors to reconstruct 3D content in the form of point clouds, meshes, or volumetric functions. However, by using the 2D priors, they are intrinsically limited to only recovering the visual parts. Highly occluded hair structures can not be reconstructed with those methods, and they only model the ''outer shell'', which is not ready to be used in physics-based rendering or simulation pipelines. In contrast, we propose a first text-guided generative method that uses 3D hair strands as an underlying representation. Leveraging 2D visual question-answering (VQA) systems, we automatically annotate synthetic hair models that are generated from a small set of artist-created hairstyles. This allows us to train a latent diffusion model that operates in a common hairstyle UV space. In qualitative and quantitative studies, we demonstrate the capabilities of the proposed model and compare it to existing hairstyle generation approaches., Comment: For more results please refer to the project page https://haar.is.tue.mpg.de/

The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating humans in global coordinates often assumes a flat ground plane and produces foot sliding. Third, the most accurate methods rely on computationally expensive optimization pipelines, limiting their use to offline applications. Finally, existing video-based methods are surprisingly less accurate than single-frame methods. We address these limitations with WHAM (World-grounded Humans with Accurate Motion), which accurately and efficiently reconstructs 3D human motion in a global coordinate system from video. WHAM learns to lift 2D keypoint sequences to 3D using motion capture data and fuses this with video features, integrating motion context and visual information. WHAM exploits camera angular velocity estimated from a SLAM method together with human motion to estimate the body's global trajectory. We combine this with a contact-aware trajectory refinement method that lets WHAM capture human motion in diverse conditions, such as climbing stairs. WHAM outperforms all existing 3D human motion recovery methods across multiple in-the-wild benchmarks. Code will be available for research purposes at http://wham.is.tue.mpg.de/

Existing methods for synthesizing 3D human gestures from speech have shown promising results, but they do not explicitly model the impact of emotions on the generated gestures. Instead, these methods directly output animations from speech without control over the expressed emotion. To address this limitation, we present AMUSE, an emotional speech-driven body animation model based on latent diffusion. Our observation is that content (i.e., gestures related to speech rhythm and word utterances), emotion, and personal style are separable. To account for this, AMUSE maps the driving audio to three disentangled latent vectors: one for content, one for emotion, and one for personal style. A latent diffusion model, trained to generate gesture motion sequences, is then conditioned on these latent vectors. Once trained, AMUSE synthesizes 3D human gestures directly from speech with control over the expressed emotions and style by combining the content from the driving speech with the emotion and style of another speech sequence. Randomly sampling the noise of the diffusion model further generates variations of the gesture with the same emotional expressivity. Qualitative, quantitative, and perceptual evaluations demonstrate that AMUSE outputs realistic gesture sequences. Compared to the state of the art, the generated gestures are better synchronized with the speech content, and better represent the emotion expressed by the input speech. Our code is available at amuse.is.tue.mpg.de., Comment: Conference on Computer Vision and Pattern Recognition (CVPR) 2024. Webpage: https://amuse.is.tue.mpg.de/

We introduce ChatPose, a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from a single image or a brief description, a process that intertwines image interpretation, world knowledge, and an understanding of body language. Traditional human pose estimation and generation methods often operate in isolation, lacking semantic understanding and reasoning abilities. ChatPose addresses these limitations by embedding SMPL poses as distinct signal tokens within a multimodal LLM, enabling the direct generation of 3D body poses from both textual and visual inputs. Leveraging the powerful capabilities of multimodal LLMs, ChatPose unifies classical 3D human pose and generation tasks while offering user interactions. Additionally, ChatPose empowers LLMs to apply their extensive world knowledge in reasoning about human poses, leading to two advanced tasks: speculative pose generation and reasoning about pose estimation. These tasks involve reasoning about humans to generate 3D poses from subtle text queries, possibly accompanied by images. We establish benchmarks for these tasks, moving beyond traditional 3D pose generation and estimation methods. Our results show that ChatPose outperforms existing multimodal LLMs and task-specific methods on these newly proposed tasks. Furthermore, ChatPose's ability to understand and generate 3D human poses based on complex reasoning opens new directions in human pose analysis., Comment: Home page: https://yfeng95.github.io/ChatPose/

Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters due to the high dimensionality of orthogonal matrices. To address this, we start by examining OFT from an information transmission perspective, and then identify a few key desiderata that enable better parameter-efficiency. Inspired by how the Cooley-Tukey fast Fourier transform algorithm enables efficient information transmission, we propose an efficient orthogonal parameterization using butterfly structures. We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT). By subsuming OFT as a special case, BOFT introduces a generalized orthogonal finetuning framework. Finally, we conduct an extensive empirical study of adapting large vision transformers, large language models, and text-to-image diffusion models to various downstream tasks in vision and language., Comment: ICLR 2024 (v2: 34 pages, 19 figures)

Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are geometrically accurate, realistic, relightable, and compatible with current rendering systems. While 3D meshes enable efficient processing and are highly portable, they lack realism in terms of shape and appearance. Neural representations, on the other hand, are realistic but lack compatibility and are slow to train and render. Our key insight is that it is possible to efficiently learn high-fidelity 3D mesh representations via differentiable rendering by exploiting highly-optimized methods from traditional computer graphics and approximating some of the components with neural networks. To that end, we introduce FLARE, a technique that enables the creation of animatable and relightable mesh avatars from a single monocular video. First, we learn a canonical geometry using a mesh representation, enabling efficient differentiable rasterization and straightforward animation via learned blendshapes and linear blend skinning weights. Second, we follow physically-based rendering and factor observed colors into intrinsic albedo, roughness, and a neural representation of the illumination, allowing the learned avatars to be relit in novel scenes. Since our input videos are captured on a single device with a narrow field of view, modeling the surrounding environment light is non-trivial. Based on the split-sum approximation for modeling specular reflections, we address this by approximating the pre-filtered environment map with a multi-layer perceptron (MLP) modulated by the surface roughness, eliminating the need to explicitly model the light. We demonstrate that our mesh-based avatar formulation, combined with learned deformation, material, and lighting MLPs, produces avatars with high-quality geometry and appearance, while also being efficient to train and render compared to existing approaches., Comment: 15 pages, Accepted: ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2023

The creation of photorealistic virtual worlds requires the accurate modeling of 3D surface geometry for a wide range of objects. For this, meshes are appealing since they 1) enable fast physics-based rendering with realistic material and lighting, 2) support physical simulation, and 3) are memory-efficient for modern graphics pipelines. Recent work on reconstructing and statistically modeling 3D shape, however, has critiqued meshes as being topologically inflexible. To capture a wide range of object shapes, any 3D representation must be able to model solid, watertight, shapes as well as thin, open, surfaces. Recent work has focused on the former, and methods for reconstructing open surfaces do not support fast reconstruction with material and lighting or unconditional generative modelling. Inspired by the observation that open surfaces can be seen as islands floating on watertight surfaces, we parameterize open surfaces by defining a manifold signed distance field on watertight templates. With this parameterization, we further develop a grid-based and differentiable representation that parameterizes both watertight and non-watertight meshes of arbitrary topology. Our new representation, called Ghost-on-the-Shell (G-Shell), enables two important applications: differentiable rasterization-based reconstruction from multiview images and generative modelling of non-watertight meshes. We empirically demonstrate that G-Shell achieves state-of-the-art performance on non-watertight mesh reconstruction and generation tasks, while also performing effectively for watertight meshes., Comment: ICLR 2024 Oral (v3: 30 pages, 19 figures, Project Page: https://gshell3d.github.io/)

We present a method to estimate human motion in a global scene from moving cameras. This is a highly challenging task due to the coupling of human and camera motions in the video. To address this problem, we propose a joint optimization framework that disentangles human and camera motions using both foreground human motion priors and background scene features. Unlike existing methods that use SLAM as initialization, we propose to tightly integrate SLAM and human motion priors in an optimization that is inspired by bundle adjustment. Specifically, we optimize human and camera motions to match both the observed human pose and scene features. This design combines the strengths of SLAM and motion priors, which leads to significant improvements in human and camera motion estimation. We additionally introduce a motion prior that is suitable for batch optimization, making our approach significantly more efficient than existing approaches. Finally, we propose a novel synthetic dataset that enables evaluating camera motion in addition to human motion from dynamic videos. Experiments on the synthetic and real-world RICH datasets demonstrate that our approach substantially outperforms prior art in recovering both human and camera motions., Comment: 3DV 2024. Project page: https://nvlabs.github.io/PACE/

In this paper, we focus on a general yet important learning problem, pairwise similarity learning (PSL). PSL subsumes a wide range of important applications, such as open-set face recognition, speaker verification, image retrieval and person re-identification. The goal of PSL is to learn a pairwise similarity function assigning a higher similarity score to positive pairs (i.e., a pair of samples with the same label) than to negative pairs (i.e., a pair of samples with different label). We start by identifying a key desideratum for PSL, and then discuss how existing methods can achieve this desideratum. We then propose a surprisingly simple proxy-free method, called SimPLE, which requires neither feature/proxy normalization nor angular margin and yet is able to generalize well in open-set recognition. We apply the proposed method to three challenging PSL tasks: open-set face recognition, image retrieval and speaker verification. Comprehensive experimental results on large-scale benchmarks show that our method performs significantly better than current state-of-the-art methods., Comment: Published in ICCV 2023 (Project page: https://simple.is.tue.mpg.de/)

Understanding how humans use physical contact to interact with the world is key to enabling human-centric artificial intelligence. While inferring 3D contact is crucial for modeling realistic and physically-plausible human-object interactions, existing methods either focus on 2D, consider body joints rather than the surface, use coarse 3D body regions, or do not generalize to in-the-wild images. In contrast, we focus on inferring dense, 3D contact between the full body surface and objects in arbitrary images. To achieve this, we first collect DAMON, a new dataset containing dense vertex-level contact annotations paired with RGB images containing complex human-object and human-scene contact. Second, we train DECO, a novel 3D contact detector that uses both body-part-driven and scene-context-driven attention to estimate vertex-level contact on the SMPL body. DECO builds on the insight that human observers recognize contact by reasoning about the contacting body parts, their proximity to scene objects, and the surrounding scene context. We perform extensive evaluations of our detector on DAMON as well as on the RICH and BEHAVE datasets. We significantly outperform existing SOTA methods across all benchmarks. We also show qualitatively that DECO generalizes well to diverse and challenging real-world human interactions in natural images. The code, data, and models are available at https://deco.is.tue.mpg.de., Comment: Accepted as Oral in ICCV'23. Project page: https://deco.is.tue.mpg.de

Our goal is to create a realistic 3D facial avatar with hair and accessories using only a text description. While this challenge has attracted significant recent interest, existing methods either lack realism, produce unrealistic shapes, or do not support editing, such as modifications to the hairstyle. We argue that existing methods are limited because they employ a monolithic modeling approach, using a single representation for the head, face, hair, and accessories. Our observation is that the hair and face, for example, have very different structural qualities that benefit from different representations. Building on this insight, we generate avatars with a compositional model, in which the head, face, and upper body are represented with traditional 3D meshes, and the hair, clothing, and accessories with neural radiance fields (NeRF). The model-based mesh representation provides a strong geometric prior for the face region, improving realism while enabling editing of the person's appearance. By using NeRFs to represent the remaining components, our method is able to model and synthesize parts with complex geometry and appearance, such as curly hair and fluffy scarves. Our novel system synthesizes these high-quality compositional avatars from text descriptions. The experimental results demonstrate that our method, Text-guided generation and Editing of Compositional Avatars (TECA), produces avatars that are more realistic than those of recent methods while being editable because of their compositional nature. For example, our TECA enables the seamless transfer of compositional features like hairstyles, scarves, and other accessories between avatars. This capability supports applications such as virtual try-on., Comment: Home page: https://yfeng95.github.io/teca

Tremendous efforts have been made to learn animatable and photorealistic human avatars. Towards this end, both explicit and implicit 3D representations are heavily studied for a holistic modeling and capture of the whole human (e.g., body, clothing, face and hair), but neither representation is an optimal choice in terms of representation efficacy since different parts of the human avatar have different modeling desiderata. For example, meshes are generally not suitable for modeling clothing and hair. Motivated by this, we present Disentangled Avatars~(DELTA), which models humans with hybrid explicit-implicit 3D representations. DELTA takes a monocular RGB video as input, and produces a human avatar with separate body and clothing/hair layers. Specifically, we demonstrate two important applications for DELTA. For the first one, we consider the disentanglement of the human body and clothing and in the second, we disentangle the face and hair. To do so, DELTA represents the body or face with an explicit mesh-based parametric 3D model and the clothing or hair with an implicit neural radiance field. To make this possible, we design an end-to-end differentiable renderer that integrates meshes into volumetric rendering, enabling DELTA to learn directly from monocular videos without any 3D supervision. Finally, we show that how these two applications can be easily combined to model full-body avatars, such that the hair, face, body and clothing can be fully disentangled yet jointly rendered. Such a disentanglement enables hair and clothing transfer to arbitrary body shapes. We empirically validate the effectiveness of DELTA's disentanglement by demonstrating its promising performance on disentangled reconstruction, virtual clothing try-on and hairstyle transfer. To facilitate future research, we also release an open-sourced pipeline for the study of hybrid human avatar modeling., Comment: home page: https://yfeng95.github.io/delta. arXiv admin note: text overlap with arXiv:2210.01868

The regression of 3D Human Pose and Shape (HPS) from an image is becoming increasingly accurate. This makes the results useful for downstream tasks like human action recognition or 3D graphics. Yet, no regressor is perfect, and accuracy can be affected by ambiguous image evidence or by poses and appearance that are unseen during training. Most current HPS regressors, however, do not report the confidence of their outputs, meaning that downstream tasks cannot differentiate accurate estimates from inaccurate ones. To address this, we develop POCO, a novel framework for training HPS regressors to estimate not only a 3D human body, but also their confidence, in a single feed-forward pass. Specifically, POCO estimates both the 3D body pose and a per-sample variance. The key idea is to introduce a Dual Conditioning Strategy (DCS) for regressing uncertainty that is highly correlated to pose reconstruction quality. The POCO framework can be applied to any HPS regressor and here we evaluate it by modifying HMR, PARE, and CLIFF. In all cases, training the network to reason about uncertainty helps it learn to more accurately estimate 3D pose. While this was not our goal, the improvement is modest but consistent. Our main motivation is to provide uncertainty estimates for downstream tasks; we demonstrate this in two ways: (1) We use the confidence estimates to bootstrap HPS training. Given unlabelled image data, we take the confident estimates of a POCO-trained regressor as pseudo ground truth. Retraining with this automatically-curated data improves accuracy. (2) We exploit uncertainty in video pose estimation by automatically identifying uncertain frames (e.g. due to occlusion) and inpainting these from confident frames. Code and models will be available for research at https://poco.is.tue.mpg.de.

Hands are dexterous and highly versatile manipulators that are central to how humans interact with objects and their environment. Consequently, modeling realistic hand-object interactions, including the subtle motion of individual fingers, is critical for applications in computer graphics, computer vision, and mixed reality. Prior work on capturing and modeling humans interacting with objects in 3D focuses on the body and object motion, often ignoring hand pose. In contrast, we introduce GRIP, a learning-based method that takes, as input, the 3D motion of the body and the object, and synthesizes realistic motion for both hands before, during, and after object interaction. As a preliminary step before synthesizing the hand motion, we first use a network, ANet, to denoise the arm motion. Then, we leverage the spatio-temporal relationship between the body and the object to extract two types of novel temporal interaction cues, and use them in a two-stage inference pipeline to generate the hand motion. In the first stage, we introduce a new approach to enforce motion temporal consistency in the latent space (LTC), and generate consistent interaction motions. In the second stage, GRIP generates refined hand poses to avoid hand-object penetrations. Given sequences of noisy body and object motion, GRIP upgrades them to include hand-object interaction. Quantitative experiments and perceptual studies demonstrate that GRIP outperforms baseline methods and generalizes to unseen objects and motions from different motion-capture datasets., Comment: The project has been started during Omid Taheri's internship at Adobe and as a collaboration with the Max Planck Institute for Intelligent Systems

We introduce TADA, a simple-yet-effective approach that takes textual descriptions and produces expressive 3D avatars with high-quality geometry and lifelike textures, that can be animated and rendered with traditional graphics pipelines. Existing text-based character generation methods are limited in terms of geometry and texture quality, and cannot be realistically animated due to inconsistent alignment between the geometry and the texture, particularly in the face region. To overcome these limitations, TADA leverages the synergy of a 2D diffusion model and an animatable parametric body model. Specifically, we derive an optimizable high-resolution body model from SMPL-X with 3D displacements and a texture map, and use hierarchical rendering with score distillation sampling (SDS) to create high-quality, detailed, holistic 3D avatars from text. To ensure alignment between the geometry and texture, we render normals and RGB images of the generated character and exploit their latent embeddings in the SDS training process. We further introduce various expression parameters to deform the generated character during training, ensuring that the semantics of our generated character remain consistent with the original SMPL-X model, resulting in an animatable character. Comprehensive evaluations demonstrate that TADA significantly surpasses existing approaches on both qualitative and quantitative measures. TADA enables creation of large-scale digital character assets that are ready for animation and rendering, while also being easily editable through natural language. The code will be public for research purposes.

We present SCULPT, a novel 3D generative model for clothed and textured 3D meshes of humans. Specifically, we devise a deep neural network that learns to represent the geometry and appearance distribution of clothed human bodies. Training such a model is challenging, as datasets of textured 3D meshes for humans are limited in size and accessibility. Our key observation is that there exist medium-sized 3D scan datasets like CAPE, as well as large-scale 2D image datasets of clothed humans and multiple appearances can be mapped to a single geometry. To effectively learn from the two data modalities, we propose an unpaired learning procedure for pose-dependent clothed and textured human meshes. Specifically, we learn a pose-dependent geometry space from 3D scan data. We represent this as per vertex displacements w.r.t. the SMPL model. Next, we train a geometry conditioned texture generator in an unsupervised way using the 2D image data. We use intermediate activations of the learned geometry model to condition our texture generator. To alleviate entanglement between pose and clothing type, and pose and clothing appearance, we condition both the texture and geometry generators with attribute labels such as clothing types for the geometry, and clothing colors for the texture generator. We automatically generated these conditioning labels for the 2D images based on the visual question answering model BLIP and CLIP. We validate our method on the SCULPT dataset, and compare to state-of-the-art 3D generative models for clothed human bodies. Our code and data can be found at https://sculpt.is.tue.mpg.de., Comment: Updated to camera ready version of CVPR 2024

Generative Adversarial Networks (GANs) can produce high-quality samples, but do not provide an estimate of the probability density around the samples. However, it has been noted that maximizing the log-likelihood within an energy-based setting can lead to an adversarial framework where the discriminator provides unnormalized density (often called energy). We further develop this perspective, incorporate importance sampling, and show that 1) Wasserstein GAN performs a biased estimate of the partition function, and we propose instead to use an unbiased estimator; and 2) when optimizing for likelihood, one must maximize generator entropy. This is hypothesized to provide a better mode coverage. Different from previous works, we explicitly compute the density of the generated samples. This is the key enabler to designing an unbiased estimator of the partition function and computation of the generator entropy term. The generator density is obtained via a new type of flow network, called one-way flow network, that is less constrained in terms of architecture, as it does not require a tractable inverse function. Our experimental results show that our method converges faster, produces comparable sample quality to GANs with similar architecture, successfully avoids over-fitting to commonly used datasets and produces smooth low-dimensional latent representations of the training data.

We show, for the first time, that neural networks trained only on synthetic data achieve state-of-the-art accuracy on the problem of 3D human pose and shape (HPS) estimation from real images. Previous synthetic datasets have been small, unrealistic, or lacked realistic clothing. Achieving sufficient realism is non-trivial and we show how to do this for full bodies in motion. Specifically, our BEDLAM dataset contains monocular RGB videos with ground-truth 3D bodies in SMPL-X format. It includes a diversity of body shapes, motions, skin tones, hair, and clothing. The clothing is realistically simulated on the moving bodies using commercial clothing physics simulation. We render varying numbers of people in realistic scenes with varied lighting and camera motions. We then train various HPS regressors using BEDLAM and achieve state-of-the-art accuracy on real-image benchmarks despite training with synthetic data. We use BEDLAM to gain insights into what model design choices are important for accuracy. With good synthetic training data, we find that a basic method like HMR approaches the accuracy of the current SOTA method (CLIFF). BEDLAM is useful for a variety of tasks and all images, ground truth bodies, 3D clothing, support code, and more are available for research purposes. Additionally, we provide detailed information about our synthetic data generation pipeline, enabling others to generate their own datasets. See the project page: https://bedlam.is.tue.mpg.de/.

Social interaction is a fundamental aspect of human behavior and communication. The way individuals position themselves in relation to others, also known as proxemics, conveys social cues and affects the dynamics of social interaction. Reconstructing such interaction from images presents challenges because of mutual occlusion and the limited availability of large training datasets. To address this, we present a novel approach that learns a prior over the 3D proxemics two people in close social interaction and demonstrate its use for single-view 3D reconstruction. We start by creating 3D training data of interacting people using image datasets with contact annotations. We then model the proxemics using a novel denoising diffusion model called BUDDI that learns the joint distribution over the poses of two people in close social interaction. Sampling from our generative proxemics model produces realistic 3D human interactions, which we validate through a perceptual study. We use BUDDI in reconstructing two people in close proximity from a single image without any contact annotation via an optimization approach that uses the diffusion model as a prior. Our approach recovers accurate and plausible 3D social interactions from noisy initial estimates, outperforming state-of-the-art methods. Our code, data, and model are availableat our project website at: muelea.github.io/buddi., Comment: Project website: muelea.github.io/buddi

To be widely adopted, 3D facial avatars must be animated easily, realistically, and directly from speech signals. While the best recent methods generate 3D animations that are synchronized with the input audio, they largely ignore the impact of emotions on facial expressions. Realistic facial animation requires lip-sync together with the natural expression of emotion. To that end, we propose EMOTE (Expressive Model Optimized for Talking with Emotion), which generates 3D talking-head avatars that maintain lip-sync from speech while enabling explicit control over the expression of emotion. To achieve this, we supervise EMOTE with decoupled losses for speech (i.e., lip-sync) and emotion. These losses are based on two key observations: (1) deformations of the face due to speech are spatially localized around the mouth and have high temporal frequency, whereas (2) facial expressions may deform the whole face and occur over longer intervals. Thus, we train EMOTE with a per-frame lip-reading loss to preserve the speech-dependent content, while supervising emotion at the sequence level. Furthermore, we employ a content-emotion exchange mechanism in order to supervise different emotions on the same audio, while maintaining the lip motion synchronized with the speech. To employ deep perceptual losses without getting undesirable artifacts, we devise a motion prior in the form of a temporal VAE. Due to the absence of high-quality aligned emotional 3D face datasets with speech, EMOTE is trained with 3D pseudo-ground-truth extracted from an emotional video dataset (i.e., MEAD). Extensive qualitative and perceptual evaluations demonstrate that EMOTE produces speech-driven facial animations with better lip-sync than state-of-the-art methods trained on the same data, while offering additional, high-quality emotional control., Comment: SIGGRAPH Asia 2023 Conference Paper

Existing methods for capturing datasets of 3D heads in dense semantic correspondence are slow, and commonly address the problem in two separate steps; multi-view stereo (MVS) reconstruction followed by non-rigid registration. To simplify this process, we introduce TEMPEH (Towards Estimation of 3D Meshes from Performances of Expressive Heads) to directly infer 3D heads in dense correspondence from calibrated multi-view images. Registering datasets of 3D scans typically requires manual parameter tuning to find the right balance between accurately fitting the scans surfaces and being robust to scanning noise and outliers. Instead, we propose to jointly register a 3D head dataset while training TEMPEH. Specifically, during training we minimize a geometric loss commonly used for surface registration, effectively leveraging TEMPEH as a regularizer. Our multi-view head inference builds on a volumetric feature representation that samples and fuses features from each view using camera calibration information. To account for partial occlusions and a large capture volume that enables head movements, we use view- and surface-aware feature fusion, and a spatial transformer-based head localization module, respectively. We use raw MVS scans as supervision during training, but, once trained, TEMPEH directly predicts 3D heads in dense correspondence without requiring scans. Predicting one head takes about 0.3 seconds with a median reconstruction error of 0.26 mm, 64% lower than the current state-of-the-art. This enables the efficient capture of large datasets containing multiple people and diverse facial motions. Code, model, and data are publicly available at https://tempeh.is.tue.mpg.de., Comment: Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Although the estimation of 3D human pose and shape (HPS) is rapidly progressing, current methods still cannot reliably estimate moving humans in global coordinates, which is critical for many applications. This is particularly challenging when the camera is also moving, entangling human and camera motion. To address these issues, we adopt a novel 5D representation (space, time, and identity) that enables end-to-end reasoning about people in scenes. Our method, called TRACE, introduces several novel architectural components. Most importantly, it uses two new "maps" to reason about the 3D trajectory of people over time in camera, and world, coordinates. An additional memory unit enables persistent tracking of people even during long occlusions. TRACE is the first one-stage method to jointly recover and track 3D humans in global coordinates from dynamic cameras. By training it end-to-end, and using full image information, TRACE achieves state-of-the-art performance on tracking and HPS benchmarks. The code and dataset are released for research purposes., Comment: Project page: https://www.yusun.work/TRACE/TRACE.html