Search

Mamba has achieved significant advantages in long-context modeling and autoregressive tasks, but its scalability with large parameters remains a major limitation in vision applications. pretraining is a widely used strategy to enhance backbone model performance. Although the success of Masked Autoencoder in Transformer pretraining is well recognized, it does not significantly improve Mamba's visual learning performance. We found that using the correct autoregressive pretraining can significantly boost the performance of the Mamba architecture. Based on this analysis, we propose Masked Autoregressive Pretraining (MAP) to pretrain a hybrid Mamba-Transformer vision backbone network. This strategy combines the strengths of both MAE and Autoregressive pretraining, improving the performance of Mamba and Transformer modules within a unified paradigm. Additionally, in terms of integrating Mamba and Transformer modules, we empirically found that inserting Transformer layers at regular intervals within Mamba layers can significantly enhance downstream task performance. Experimental results show that both the pure Mamba architecture and the hybrid Mamba-Transformer vision backbone network pretrained with MAP significantly outperform other pretraining strategies, achieving state-of-the-art performance. We validate the effectiveness of the method on both 2D and 3D datasets and provide detailed ablation studies to support the design choices for each component.

VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for understanding and generating visual content, which can lead to misalignment and increased complexity. In contrast, VILA-U employs a single autoregressive next-token prediction framework for both tasks, eliminating the need for additional components like diffusion models. This approach not only simplifies the model but also achieves near state-of-the-art performance in visual language understanding and generation. The success of VILA-U is attributed to two main factors: the unified vision tower that aligns discrete visual tokens with textual inputs during pretraining, which enhances visual perception, and autoregressive image generation can achieve similar quality as diffusion models with high-quality dataset. This allows VILA-U to perform comparably to more complex models using a fully token-based autoregressive framework., Comment: 11 pages, 7 figures, 8 tables

The synchronisation between turbulent flows in three dimensional periodic boxes is investigated through conditional and unconditional Lyapunov analyses based on the data obtained with direct numerical simulations and large eddy simulations. By systematic numerical experiments, we find that the leading Lyapunov exponents obtained with large eddy simulations follow the same scaling law as that of filtered perturbations of the real flow, thus should be interpreted as approximations of the latter. Data on the threshold coupling wavenumber for synchronisation show that the synchronisability of coupled turbulent flows is mainly determined by the conditional leading Lyapunov exponents of the slave flow itself, and is insensitive to the nature of the master flow. We present strong evidence to show that the peak wavenumber for the energy spectrum of the leading Lyapunov vector is approximately the same as the threshold wavenumber, corroborating a relationship established recently in rotating turbulence. The threshold wavenumber of large eddy simulations based on canonical subgrid-scale stress models is shown to be different from that of direct numerical simulations, even for the more sophisticated dynamical mixed model. By employing new parametrisation, the threshold wavenumbers are quantified. The care one needs to exercise to interpret the results obtained with large eddy simulations is discussed.

Understanding how humans cooperatively rearrange household objects is critical for VR/AR and human-robot interaction. However, in-depth studies on modeling these behaviors are under-researched due to the lack of relevant datasets. We fill this gap by presenting CORE4D, a novel large-scale 4D human-object-human interaction dataset focusing on collaborative object rearrangement, which encompasses diverse compositions of various object geometries, collaboration modes, and 3D scenes. With 1K human-object-human motion sequences captured in the real world, we enrich CORE4D by contributing an iterative collaboration retargeting strategy to augment motions to a variety of novel objects. Leveraging this approach, CORE4D comprises a total of 11K collaboration sequences spanning 3K real and virtual object shapes. Benefiting from extensive motion patterns provided by CORE4D, we benchmark two tasks aiming at generating human-object interaction: human-object motion forecasting and interaction synthesis. Extensive experiments demonstrate the effectiveness of our collaboration retargeting strategy and indicate that CORE4D has posed new challenges to existing human-object interaction generation methodologies. Our dataset and code are available at https://github.com/leolyliu/CORE4D-Instructions.

Recently, Patel et.al introduced a higher dimensional version of the SYK model with random coupling in Yukawa interaction to find the linear-$T$ resistivity. We test the universality of the mechanism by replacing the scalar with vector field in various dimensions. We find that it works for vector as well as scalar interaction, although the details are very different. However, this mechanism for the linear-$T$ resistivity works only in $(2+1)$ dimension not in higher dimension independent of the interaction type. Based on these results, we explore the role of spatial random disorder and find a simple understanding how such random scattering converts the Fermi liquid to the strange metal by changing the behavior of the self-energies of involved boson and fermion., Comment: 32 pages, 2 figures

Human motion synthesis is a fundamental task in computer animation. Despite recent progress in this field utilizing deep learning and motion capture data, existing methods are always limited to specific motion categories, environments, and styles. This poor generalizability can be partially attributed to the difficulty and expense of collecting large-scale and high-quality motion data. At the same time, foundation models trained with internet-scale image and text data have demonstrated surprising world knowledge and reasoning ability for various downstream tasks. Utilizing these foundation models may help with human motion synthesis, which some recent works have superficially explored. However, these methods didn't fully unveil the foundation models' potential for this task and only support several simple actions and environments. In this paper, we for the first time, without any motion data, explore open-set human motion synthesis using natural language instructions as user control signals based on MLLMs across any motion task and environment. Our framework can be split into two stages: 1) sequential keyframe generation by utilizing MLLMs as a keyframe designer and animator; 2) motion filling between keyframes through interpolation and motion tracking. Our method can achieve general human motion synthesis for many downstream tasks. The promising results demonstrate the worth of mocap-free human motion synthesis aided by MLLMs and pave the way for future research.

This paper presents a novel approach 4DRecons that takes a single camera RGB-D sequence of a dynamic subject as input and outputs a complete textured deforming 3D model over time. 4DRecons encodes the output as a 4D neural implicit surface and presents an optimization procedure that combines a data term and two regularization terms. The data term fits the 4D implicit surface to the input partial observations. We address fundamental challenges in fitting a complete implicit surface to partial observations. The first regularization term enforces that the deformation among adjacent frames is as rigid as possible (ARAP). To this end, we introduce a novel approach to compute correspondences between adjacent textured implicit surfaces, which are used to define the ARAP regularization term. The second regularization term enforces that the topology of the underlying object remains fixed over time. This regularization is critical for avoiding self-intersections that are typical in implicit-based reconstructions. We have evaluated the performance of 4DRecons on a variety of datasets. Experimental results show that 4DRecons can handle large deformations and complex inter-part interactions and outperform state-of-the-art approaches considerably.

The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However, due to high occlusions during hand-object interaction, physical plausibility remains a challenging criterion for purely vision-based tracking methods. To address this issue and enhance the results of existing hand trackers, this paper proposes a novel physically-aware hand motion de-noising method. Specifically, we introduce two learned loss terms that explicitly capture two crucial aspects of physical plausibility: grasp credibility and manipulation feasibility. These terms are used to train a physically-aware de-noising network. Qualitative and quantitative experiments demonstrate that our approach significantly improves both fine-grained physical plausibility and overall pose accuracy, surpassing current state-of-the-art de-noising methods.

In relativistic heavy-ion collisions, jet quenching in quark-gluon plasma (QGP) has been extensively studied, revealing important insights into the properties of the color deconfined nuclear matter. Over the past decade, there has been a surge of interest in the exploration of QGP droplets in small collision systems like $p$+$p$ or $p$+A collisions driven by the observation of collective flow phenomena. However, the absence of jet quenching, a key QGP signature, in these systems poses a puzzle. Understanding how jet quenching evolves with system size is crucial for uncovering the underlying physics. In this study, we employ the linear Boltzmann transport (LBT) model to investigate jet modification in $^{96}$Ru+$^{96}$Ru, $^{96}$Zr+$^{96}$Zr, and $^{197}$Au+$^{197}$Au collisions at $\sqrt{s_{NN}}=200$ GeV. Our findings highlight the system size sensitivity exhibited by jet nuclear modification factor ($R_\mathrm{AA}$) and jet shape ($\rho$), contrasting to the relatively weak responses of jet mass ($M$), girth ($g$) and momentum dispersion ($p_\mathrm{T}{D}$) to system size variations. These results offer invaluable insights into the system size dependence of the QGP properties and await experimental validation at the Relativistic Heavy-Ion Collider.

We explore the dexterous manipulation transfer problem by designing simulators. The task wishes to transfer human manipulations to dexterous robot hand simulations and is inherently difficult due to its intricate, highly-constrained, and discontinuous dynamics and the need to control a dexterous hand with a DoF to accurately replicate human manipulations. Previous approaches that optimize in high-fidelity black-box simulators or a modified one with relaxed constraints only demonstrate limited capabilities or are restricted by insufficient simulation fidelity. We introduce parameterized quasi-physical simulators and a physics curriculum to overcome these limitations. The key ideas are 1) balancing between fidelity and optimizability of the simulation via a curriculum of parameterized simulators, and 2) solving the problem in each of the simulators from the curriculum, with properties ranging from high task optimizability to high fidelity. We successfully enable a dexterous hand to track complex and diverse manipulations in high-fidelity simulated environments, boosting the success rate by 11\%+ from the best-performed baseline. The project website is available at https://meowuu7.github.io/QuasiSim/., Comment: Accepted to ECCV 2024. Project website: https://meowuu7.github.io/QuasiSim/ Code: https://github.com/Meowuu7/QuasiSim Hugging Face Demo: https://huggingface.co/spaces/xymeow7/quasi-physical-sims

We present GenN2N, a unified NeRF-to-NeRF translation framework for various NeRF translation tasks such as text-driven NeRF editing, colorization, super-resolution, inpainting, etc. Unlike previous methods designed for individual translation tasks with task-specific schemes, GenN2N achieves all these NeRF editing tasks by employing a plug-and-play image-to-image translator to perform editing in the 2D domain and lifting 2D edits into the 3D NeRF space. Since the 3D consistency of 2D edits may not be assured, we propose to model the distribution of the underlying 3D edits through a generative model that can cover all possible edited NeRFs. To model the distribution of 3D edited NeRFs from 2D edited images, we carefully design a VAE-GAN that encodes images while decoding NeRFs. The latent space is trained to align with a Gaussian distribution and the NeRFs are supervised through an adversarial loss on its renderings. To ensure the latent code does not depend on 2D viewpoints but truly reflects the 3D edits, we also regularize the latent code through a contrastive learning scheme. Extensive experiments on various editing tasks show GenN2N, as a universal framework, performs as well or better than task-specific specialists while possessing flexible generative power. More results on our project page: https://xiangyueliu.github.io/GenN2N/, Comment: Accepted to CVPR 2024. Project page: https://xiangyueliu.github.io/GenN2N/

Humanoid Reaction Synthesis is pivotal for creating highly interactive and empathetic robots that can seamlessly integrate into human environments, enhancing the way we live, work, and communicate. However, it is difficult to learn the diverse interaction patterns of multiple humans and generate physically plausible reactions. The kinematics-based approaches face challenges, including issues like floating feet, sliding, penetration, and other problems that defy physical plausibility. The existing physics-based method often relies on kinematics-based methods to generate reference states, which struggle with the challenges posed by kinematic noise during action execution. Constrained by their reliance on diffusion models, these methods are unable to achieve real-time inference. In this work, we propose a Forward Dynamics Guided 4D Imitation method to generate physically plausible human-like reactions. The learned policy is capable of generating physically plausible and human-like reactions in real-time, significantly improving the speed(x33) and quality of reactions compared with the existing method. Our experiments on the InterHuman and Chi3D datasets, along with ablation studies, demonstrate the effectiveness of our approach.

This report presents the development and results of an advanced SPH (Smoothed Particle Hydrodynamics) simulation framework, designed for high fidelity fluid dynamics modeling. Our framework, accessible at https://github.com/jason-huang03/SPH_Project, integrates various SPH algorithms including WCSPH, PCISPH, and DFSPH, alongside techniques for rigid-fluid coupling and high viscosity fluid simulations. Leveraging the computational power of CUDA and the versatility of Taichi, the framework excels in handling large-scale simulations with millions of particles. We demonstrate the capability of our framework through a series of simulations showcasing rigid-fluid coupling, high viscosity fluids, and large-scale fluid dynamics. Furthermore, a detailed performance analysis reveals CUDA's superior efficiency across different hardware platforms. This work is an exploraion into modern SPH simulation techniques, showcasing their practical implementation and capabilities.

This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM) designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages. ShapeLLM is built upon an improved 3D encoder by extending ReCon to ReCon++ that benefits from multi-view image distillation for enhanced geometry understanding. By utilizing ReCon++ as the 3D point cloud input encoder for LLMs, ShapeLLM is trained on constructed instruction-following data and tested on our newly human-curated benchmark, 3D MM-Vet. ReCon++ and ShapeLLM achieve state-of-the-art performance in 3D geometry understanding and language-unified 3D interaction tasks, such as embodied visual grounding. Project page: https://qizekun.github.io/shapellm/, Comment: Accepted at ECCV 2024

In this work, we tackle the challenging problem of denoising hand-object interactions (HOI). Given an erroneous interaction sequence, the objective is to refine the incorrect hand trajectory to remove interaction artifacts for a perceptually realistic sequence. This challenge involves intricate interaction noise, including unnatural hand poses and incorrect hand-object relations, alongside the necessity for robust generalization to new interactions and diverse noise patterns. We tackle those challenges through a novel approach, GeneOH Diffusion, incorporating two key designs: an innovative contact-centric HOI representation named GeneOH and a new domain-generalizable denoising scheme. The contact-centric representation GeneOH informatively parameterizes the HOI process, facilitating enhanced generalization across various HOI scenarios. The new denoising scheme consists of a canonical denoising model trained to project noisy data samples from a whitened noise space to a clean data manifold and a "denoising via diffusion" strategy which can handle input trajectories with various noise patterns by first diffusing them to align with the whitened noise space and cleaning via the canonical denoiser. Extensive experiments on four benchmarks with significant domain variations demonstrate the superior effectiveness of our method. GeneOH Diffusion also shows promise for various downstream applications. Project website: https://meowuu7.github.io/GeneOH-Diffusion/., Comment: Accepted to ICLR 2024. Project website: https://meowuu7.github.io/GeneOH-Diffusion/; Huggingface Demo: https://huggingface.co/spaces/xymeow7/gene-hoi-denoising; Code: https://github.com/Meowuu7/GeneOH-Diffusion

The rise of multimodal misinformation on social platforms poses significant challenges for individuals and societies. Its increased credibility and broader impact compared to textual misinformation make detection complex, requiring robust reasoning across diverse media types and profound knowledge for accurate verification. The emergence of Large Vision Language Model (LVLM) offers a potential solution to this problem. Leveraging their proficiency in processing visual and textual information, LVLM demonstrates promising capabilities in recognizing complex information and exhibiting strong reasoning skills. In this paper, we first investigate the potential of LVLM on multimodal misinformation detection. We find that even though LVLM has a superior performance compared to LLMs, its profound reasoning may present limited power with a lack of evidence. Based on these observations, we propose LEMMA: LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation. LEMMA leverages LVLM intuition and reasoning capabilities while augmenting them with external knowledge to enhance the accuracy of misinformation detection. Our method improves the accuracy over the top baseline LVLM by 7% and 13% on Twitter and Fakeddit datasets respectively.

Estimating 3D full-body pose from sparse sensor data is a pivotal technique employed for the reconstruction of realistic human motions in Augmented Reality and Virtual Reality. However, translating sparse sensor signals into comprehensive human motion remains a challenge since the sparsely distributed sensors in common VR systems fail to capture the motion of full human body. In this paper, we use well-designed Body Pose Graph (BPG) to represent the human body and translate the challenge into a prediction problem of graph missing nodes. Then, we propose a novel full-body motion reconstruction framework based on BPG. To establish BPG, nodes are initially endowed with features extracted from sparse sensor signals. Features from identifiable joint nodes across diverse sensors are amalgamated and processed from both temporal and spatial perspectives. Temporal dynamics are captured using the Temporal Pyramid Structure, while spatial relations in joint movements inform the spatial attributes. The resultant features serve as the foundational elements of the BPG nodes. To further refine the BPG, node features are updated through a graph neural network that incorporates edge reflecting varying joint relations. Our method's effectiveness is evidenced by the attained state-of-the-art performance, particularly in lower body motion, outperforming other baseline methods. Additionally, an ablation study validates the efficacy of each module in our proposed framework.

This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations due to data scarcity and challenges in label acquisition. To address these issues, we propose a self-supervised learning method that leverages the cross-modal relationship between point cloud videos and image videos to acquire meaningful feature representations. Intra-modal and cross-modal contrastive learning techniques are employed to facilitate effective comprehension of point cloud video. We also propose a multi-level contrastive approach for both modalities. Through extensive experiments, we demonstrate that our method significantly surpasses previous state-of-the-art approaches, and we conduct comprehensive ablation studies to validate the effectiveness of our proposed designs.

Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and synthesizing hand-object manipulation are mostly limited to handling a single hand and object due to the lack of data support. To address this, we construct TACO, an extensive bimanual hand-object-interaction dataset spanning a large variety of tool-action-object compositions for daily human activities. TACO contains 2.5K motion sequences paired with third-person and egocentric views, precise hand-object 3D meshes, and action labels. To rapidly expand the data scale, we present a fully automatic data acquisition pipeline combining multi-view sensing with an optical motion capture system. With the vast research fields provided by TACO, we benchmark three generalizable hand-object-interaction tasks: compositional action recognition, generalizable hand-object motion forecasting, and cooperative grasp synthesis. Extensive experiments reveal new insights, challenges, and opportunities for advancing the studies of generalizable hand-object motion analysis and synthesis. Our data and code are available at https://taco2024.github.io.

In relativistic heavy-ion collisions, a hot and dense state of matter, called the Quark-Gluon Plasma (QGP), is produced. Semi-inclusive jets recoiling from trigger hadrons of high transverse momenta ($p_{\mathrm{T}}$) can serve as an effective probe of the QGP properties, as they are expected to experience jet quenching when traversing the QGP. Recent experimental results on the ratio of recoil jet yields normalized by the trigger counts in heavy-ion collisions to that in $p$+$p$ collisions ($I_{\mathrm{AA}}$) pose an unexpected challenge in its interpretation. It is observed that $I_{\mathrm{AA}}$ rises with the jet $p_{\mathrm{T}}$ and possibly exceeds unity at high $p_{\mathrm{T}}$, while traditionally it is expected that jet quenching would lead to $I_{\mathrm{AA}} < 1$. To address this challenge, we utilize the Linear Boltzmann Transport (LBT) model to simulate jet transport in the QGP, and study the effect of jet quenching for high-$p_{\mathrm{T}}$ triggers and recoil jets separately on $I_{\mathrm{AA}}$. We find that the quenching of the colored triggers alone is responsible for the rising trend and larger-than-unity value observed experimentally., Comment: 4 pages, 4 figures

This paper presents GenH2R, a framework for learning generalizable vision-based human-to-robot (H2R) handover skills. The goal is to equip robots with the ability to reliably receive objects with unseen geometry handed over by humans in various complex trajectories. We acquire such generalizability by learning H2R handover at scale with a comprehensive solution including procedural simulation assets creation, automated demonstration generation, and effective imitation learning. We leverage large-scale 3D model repositories, dexterous grasp generation methods, and curve-based 3D animation to create an H2R handover simulation environment named \simabbns, surpassing the number of scenes in existing simulators by three orders of magnitude. We further introduce a distillation-friendly demonstration generation method that automatically generates a million high-quality demonstrations suitable for learning. Finally, we present a 4D imitation learning method augmented by a future forecasting objective to distill demonstrations into a visuo-motor handover policy. Experimental evaluations in both simulators and the real world demonstrate significant improvements (at least +10\% success rate) over baselines in all cases. The project page is https://GenH2R.github.io/., Comment: The project page is https://GenH2R.github.io/, accepted by CVPR2024

We focus on the human-humanoid interaction task optionally with an object. We propose a new task named online full-body motion reaction synthesis, which generates humanoid reactions based on the human actor's motions. The previous work only focuses on human interaction without objects and generates body reactions without hand. Besides, they also do not consider the task as an online setting, which means the inability to observe information beyond the current moment in practical situations. To support this task, we construct two datasets named HHI and CoChair and propose a unified method. Specifically, we propose to construct a social affordance representation. We first select a social affordance carrier and use SE(3)-Equivariant Neural Networks to learn the local frame for the carrier, then we canonicalize the social affordance. Besides, we propose a social affordance forecasting scheme to enable the reactor to predict based on the imagined future. Experiments demonstrate that our approach can effectively generate high-quality reactions on HHI and CoChair. Furthermore, we also validate our method on existing human interaction datasets Interhuman and Chi3D.

We study a new problem of semantic complete scene forecasting (SCSF) in this work. Given a 4D dynamic point cloud sequence, our goal is to forecast the complete scene corresponding to the future next frame along with its semantic labels. To tackle this challenging problem, we properly model the synergetic relationship between future forecasting and semantic scene completion through a novel network named SCSFNet. SCSFNet leverages a hybrid geometric representation for high-resolution complete scene forecasting. To leverage multi-frame observation as well as the understanding of scene dynamics to ease the completion task, SCSFNet introduces an attention-based skip connection scheme. To ease the need to model occlusion variations and to better focus on the occluded part, SCSFNet utilizes auxiliary visibility grids to guide the forecasting task. To evaluate the effectiveness of SCSFNet, we conduct experiments on various benchmarks including two large-scale indoor benchmarks we contributed and the outdoor SemanticKITTI benchmark. Extensive experiments show SCSFNet outperforms baseline methods on multiple metrics by a large margin, and also prove the synergy between future forecasting and semantic scene completion., Comment: AAAI 2024, see https://scsfnet.github.io/

In this study, we are interested in imbuing robots with the capability of physically-grounded task planning. Recent advancements have shown that large language models (LLMs) possess extensive knowledge useful in robotic tasks, especially in reasoning and planning. However, LLMs are constrained by their lack of world grounding and dependence on external affordance models to perceive environmental information, which cannot jointly reason with LLMs. We argue that a task planner should be an inherently grounded, unified multimodal system. To this end, we introduce Robotic Vision-Language Planning (ViLa), a novel approach for long-horizon robotic planning that leverages vision-language models (VLMs) to generate a sequence of actionable steps. ViLa directly integrates perceptual data into its reasoning and planning process, enabling a profound understanding of commonsense knowledge in the visual world, including spatial layouts and object attributes. It also supports flexible multimodal goal specification and naturally incorporates visual feedback. Our extensive evaluation, conducted in both real-robot and simulated environments, demonstrates ViLa's superiority over existing LLM-based planners, highlighting its effectiveness in a wide array of open-world manipulation tasks., Comment: arXiv v2: add appendix

We study the emergent dynamics of an anisotropic universe in the context of Group Field Theory condensate cosmology, with a scalar field playing the role of a relational clock. According to different definitions of ``isotropy'', two anisotropic condensate states are considered and the Bianchi-like dynamics of cosmological anisotropic observables, as well as their quantum fluctuations, are analysed. We find that both anisotropic states become isotropic at late time, reproducing an effective Friedmann dynamics, while anisotropies give small but non-negligible contributions at earlier times, closer to the cosmic bounce., Comment: 34 pages, 16 figures

With advancements in natural language processing (NLP) models, automatic explanation generation has been proposed to mitigate misinformation on social media platforms in addition to adding warning labels to identified fake news. While many researchers have focused on generating good explanations, how these explanations can really help humans combat fake news is under-explored. In this study, we compare the effectiveness of a warning label and the state-of-the-art counterfactual explanations generated by GPT-4 in debunking misinformation. In a two-wave, online human-subject study, participants (N = 215) were randomly assigned to a control group in which false contents are shown without any intervention, a warning tag group in which the false claims were labeled, or an explanation group in which the false contents were accompanied by GPT-4 generated explanations. Our results show that both interventions significantly decrease participants' self-reported belief in fake claims in an equivalent manner for the short-term and long-term. We discuss the implications of our findings and directions for future NLP-based misinformation debunking strategies., Comment: EMNLP Findings 2023

Understanding 4D point cloud sequences online is of significant practical value in various scenarios such as VR/AR, robotics, and autonomous driving. The key goal is to continuously analyze the geometry and dynamics of a 3D scene as unstructured and redundant point cloud sequences arrive. And the main challenge is to effectively model the long-term history while keeping computational costs manageable. To tackle these challenges, we introduce a generic online 4D perception paradigm called NSM4D. NSM4D serves as a plug-and-play strategy that can be adapted to existing 4D backbones, significantly enhancing their online perception capabilities for both indoor and outdoor scenarios. To efficiently capture the redundant 4D history, we propose a neural scene model that factorizes geometry and motion information by constructing geometry tokens separately storing geometry and motion features. Exploiting the history becomes as straightforward as querying the neural scene model. As the sequence progresses, the neural scene model dynamically deforms to align with new observations, effectively providing the historical context and updating itself with the new observations. By employing token representation, NSM4D also exhibits robustness to low-level sensor noise and maintains a compact size through a geometric sampling scheme. We integrate NSM4D with state-of-the-art 4D perception backbones, demonstrating significant improvements on various online perception benchmarks in indoor and outdoor settings. Notably, we achieve a 9.6% accuracy improvement for HOI4D online action segmentation and a 3.4% mIoU improvement for SemanticKITTI online semantic segmentation. Furthermore, we show that NSM4D inherently offers excellent scalability to longer sequences beyond the training set, which is crucial for real-world applications.

This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation. DreamLLM operates on two fundamental principles. The first focuses on the generative modeling of both language and image posteriors by direct sampling in the raw multimodal space. This approach circumvents the limitations and information loss inherent to external feature extractors like CLIP, and a more thorough multimodal understanding is obtained. Second, DreamLLM fosters the generation of raw, interleaved documents, modeling both text and image contents, along with unstructured layouts. This allows DreamLLM to learn all conditional, marginal, and joint multimodal distributions effectively. As a result, DreamLLM is the first MLLM capable of generating free-form interleaved content. Comprehensive experiments highlight DreamLLM's superior performance as a zero-shot multimodal generalist, reaping from the enhanced learning synergy. Project page: https://dreamllm.github.io., Comment: ICLR 2024 (Spotlight)

Transparent objects are common in daily life. However, depth sensing for transparent objects remains a challenging problem. While learning-based methods can leverage shape priors to improve the sensing quality, the labor-intensive data collection in the real world and the sim-to-real domain gap restrict these methods' scalability. In this paper, we propose a method to finetune a stereo network with sparse depth labels automatically collected using a probing system with tactile feedback. We present a novel utility function to evaluate the benefit of touches. By approximating and optimizing the utility function, we can optimize the probing locations given a fixed touching budget to better improve the network's performance on real objects. We further combine tactile depth supervision with a confidence-based regularization to prevent over-fitting during finetuning. To evaluate the effectiveness of our method, we construct a real-world dataset including both diffuse and transparent objects. Experimental results on this dataset show that our method can significantly improve real-world depth sensing accuracy, especially for transparent objects., Comment: Accepted to the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric consistency to achieve spatial alignment, neglecting temporal consistency. To address this issue, the Transporter method was introduced for 2D data, which reconstructs the target frame from the source frame to incorporate both spatial and temporal information. However, the direct application of the Transporter to 3D point clouds is infeasible due to their structural differences from 2D images. Thus, we propose the first 3D version of the Transporter, which leverages hybrid 3D representation, cross attention, and implicit reconstruction. We apply this new learning system on 3D articulated objects and nonrigid animals (humans and rodents) and show that learned keypoints are spatio-temporally consistent. Additionally, we propose a closed-loop control strategy that utilizes the learned keypoints for 3D object manipulation and demonstrate its superior performance. Codes are available at https://github.com/zhongcl-thu/3D-Implicit-Transporter., Comment: ICCV2023 oral paper

We study the problem of few-shot physically-aware articulated mesh generation. By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical validity. Previous mesh generative models either have difficulties in depicting a diverse data space from only a few examples or fail to ensure physical validity of their samples. Regarding the above challenges, we propose two key innovations, including 1) a hierarchical mesh deformation-based generative model based upon the divide-and-conquer philosophy to alleviate the few-shot challenge by borrowing transferrable deformation patterns from large scale rigid meshes and 2) a physics-aware deformation correction scheme to encourage physically plausible generations. We conduct extensive experiments on 6 articulated categories to demonstrate the superiority of our method in generating articulated meshes with better diversity, higher visual fidelity, and better physical validity over previous methods in the few-shot setting. Further, we validate solid contributions of our two innovations in the ablation study. Project page with code is available at https://meowuu7.github.io/few-arti-obj-gen., Comment: ICCV 2023. Project Page: https://meowuu7.github.io/few-arti-obj-gen