Search

Capturing the interactions between humans and their environment in 3D is important for many applications in robotics, graphics, and vision. Recent works to reconstruct the 3D human and object from a single RGB image do not have consistent relative translation across frames because they assume a fixed depth. Moreover, their performance drops significantly when the object is occluded. In this work, we propose a novel method to track the 3D human, object, contacts between them, and their relative translation across frames from a single RGB camera, while being robust to heavy occlusions. Our method is built on two key insights. First, we condition our neural field reconstructions for human and object on per-frame SMPL model estimates obtained by pre-fitting SMPL to a video sequence. This improves neural reconstruction accuracy and produces coherent relative translation across frames. Second, human and object motion from visible frames provides valuable information to infer the occluded object. We propose a novel transformer-based neural network that explicitly uses object visibility and human motion to leverage neighbouring frames to make predictions for the occluded frames. Building on these insights, our method is able to track both human and object robustly even under occlusions. Experiments on two datasets show that our method significantly improves over the state-of-the-art methods. Our code and pretrained models are available at: https://virtualhumans.mpi-inf.mpg.de/VisTracker, accepted to CVPR 2023

Cell therapies have significant therapeutic potential in diverse fields including regenerative medicine, transplantation tolerance, and autoimmunity. Within these fields, regulatory T cells (Treg) have been deployed to ameliorate aberrant immune responses with great success. However, translation of the cryopreservation strategies employed for other cell therapy products, such as effector T cell therapies, to Treg therapies has been challenging. The lack of an optimized cryopreservation strategy for Treg products presents a substantial obstacle to their broader application, particularly as administration of fresh cells limits the window available for sterility and functional assessment. In this study, we aimed to develop an optimized cryopreservation strategy for our CD4+CD25+Foxp3+ Treg clinical product. We investigate the effect of synthetic or organic cryoprotectants including different concentrations of DMSO on Treg recovery, viability, phenotype, cytokine production, suppressive capacity, and in vivo survival following GMP-compliant manufacture. We additionally assess the effect of adding the extracellular cryoprotectant polyethylene glycol (PEG), or priming cellular expression of heat shock proteins as strategies to improve viability. We find that cryopreservation in serum-free freezing medium supplemented with 10% human serum albumin and 5% DMSO facilitates improved Treg recovery and functionality and supports a reduced DMSO concentration in Treg cryopreservation protocols. This strategy may be easily incorporated into clinical manufacture protocols for future studies.

LP2 is a 4, 7 D, L lanthionine-stabilized analog of angiotensin-(1−7), with an N-terminal D-lysine, resistant to breakdown by peptidases. It is a specific agonist of the angiotensin II type 2 receptor. Consistent with its high specificity and stability, LP2 has shown excellent safety and pharmacokinetics in a first-in-human clinical phase Ia trial. Here, based on strong rationales, we studied the capacity of LP2 to inhibit the growth of patient-derived xenografts of colorectal cancer in mice. Prior to efficacy studies, immunohistochemistry on an untreated tissue array demonstrated that the AT2R expression is reduced in human colorectal cancer and in stroma when compared to tumor adjacent tissue. Subsequent studies demonstrated that LP2 at a subcutaneously injected dose as low as 0.2 µg/kg/day inhibited patient-derived xenografts of colorectal carcinoma in mice. Kinome analyses and validation of elected kinase inhibition indicated that LP2-mediated AT2R stimulation inhibited PI3K/AKT/mTOR which resulted in apoptosis via CDKs. LP2 acted synergistically with 5-FU and the EGFR inhibitor erlotinib. Taken together, the extremely low dose of LP2 at which antitumor activity is exerted, the synergism with selected drugs and, together with its excellent specificity, safety and stability, warrant further evaluation of LP2′s inhibitory potential of colorectal cancer.

In everyday lives, humans naturally modify the surrounding environmentthrough interactions, e.g., moving a chair to sit on it. To reproduce suchinteractions in virtual spaces (e.g., metaverse), we need to be able to captureand model them, including changes in the scene geometry, ideally fromego-centric input alone (head camera and body-worn inertial sensors). This isan extremely hard problem, especially since the object/scene might not bevisible from the head camera (e.g., a human not looking at a chair whilesitting down, or not looking at the door handle while opening a door). In thispaper, we present HOPS, the first method to capture interactions such asdragging objects and opening doors from ego-centric data alone. Central to ourmethod is reasoning about human-object interactions, allowing to track objectseven when they are not visible from the head camera. HOPS localizes andregisters both the human and the dynamic object in a pre-scanned static scene.HOPS is an important first step towards advanced AR/VR applications based onimmersive virtual universes, and can provide human-centric training data toteach machines to interact with their surroundings. The supplementary video,data, and code will be available on our project page athttp://virtualhumans.mpi-inf.mpg.de/hops/

Photo-real digital human avatars are of enormous importance in graphics, asthey enable immersive communication over the globe, improve gaming andentertainment experiences, and can be particularly beneficial for AR and VRsettings. However, current avatar generation approaches either fall short inhigh-fidelity novel view synthesis, generalization to novel motions,reproduction of loose clothing, or they cannot render characters at the highresolution offered by modern displays. To this end, we propose HDHumans, whichis the first method for HD human character synthesis that jointly produces anaccurate and temporally coherent 3D deforming surface and highlyphoto-realistic images of arbitrary novel views and of motions not seen attraining time. At the technical core, our method tightly integrates a classicaldeforming character template with neural radiance fields (NeRF). Our method iscarefully designed to achieve a synergy between classical surface deformationand NeRF. First, the template guides the NeRF, which allows synthesizing novelviews of a highly dynamic and articulated character and even enables thesynthesis of novel motions. Second, we also leverage the dense pointcloudsresulting from NeRF to further improve the deforming surface via 3D-to-3Dsupervision. We outperform the state of the art quantitatively andqualitatively in terms of synthesis quality and resolution, as well as thequality of 3D surface reconstruction.

We present TOCH, a method for refining incorrect 3D hand-object interaction sequences using a data prior. Existing hand trackers, especially those that rely on very few cameras, often produce visually unrealistic results with hand-object intersection or missing contacts. Although correcting such errors requires reasoning about temporal aspects of interaction, most previous work focus on static grasps and contacts. The core of our method are TOCH fields, a novel spatio-temporal representation for modeling correspondences between hands and objects during interaction. The key component is a point-wise object-centric representation which encodes the hand position relative to the object. Leveraging this novel representation, we learn a latent manifold of plausible TOCH fields with a temporal denoising auto-encoder. Experiments demonstrate that TOCH outperforms state-of-the-art (SOTA) 3D hand-object interaction models, which are limited to static grasps and contacts. More importantly, our method produces smooth interactions even before and after contact. Using a single trained TOCH model, we quantitatively and qualitatively demonstrate its usefulness for 1) correcting erroneous reconstruction results from off-the-shelf RGB/RGB-D hand-object reconstruction methods, 2) de-noising, and 3) grasp transfer across objects. We will release our code and trained model on our project page at http://virtualhumans.mpi-inf.mpg.de/toch/

We present Neural Generalized Implicit Functions(Neural-GIF), to animate people in clothing as a function of the body pose. Given a sequence of scans of a subject in various poses, we learn to animate the character for new poses. Existing methods have relied on template-based representations of the human body (or clothing). However such models usually have fixed and limited resolutions, require difficult data pre-processing steps and cannot be used with complex clothing. We draw inspiration from template-based methods, which factorize motion into articulation and non-rigid deformation, but generalize this concept for implicit shape learning to obtain a more flexible model. We learn to map every point in the space to a canonical space, where a learned deformation field is applied to model non-rigid effects, before evaluating the signed distance field. Our formulation allows the learning of complex and non-rigid deformations of clothing and soft tissue, without computing a template registration as it is common with current approaches. Neural-GIF can be trained on raw 3D scans and reconstructs detailed complex surface geometry and deformations. Moreover, the model can generalize to new poses. We evaluate our method on a variety of characters from different public datasets in diverse clothing styles and show significant improvements over baseline methods, quantitatively and qualitatively. We also extend our model to multiple shape setting. To stimulate further research, we will make the model, code and data publicly available at: https://virtualhumans.mpi-inf.mpg.de/neuralgif/

Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when the data is not carefully aligned to a canonical orientation. Aligning real world 3D data collected from different sources is non-trivial and requires manual intervention. In this paper, we propose the Adjoint Rigid Transform (ART) Network, a neural module which can be integrated with a variety of 3D networks to significantly boost their performance. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks such as shape reconstruction, interpolation, non-rigid registration, and latent disentanglement. ART achieves this with self-supervision and a rotation equivariance constraint on predicted rotations. The remarkable result is that with only self-supervision, ART facilitates learning a unique canonical orientation for both rigid and nonrigid shapes, which leads to a notable boost in performance of aforementioned tasks. We will release our code and pre-trained models for further research.

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in resolution, and ability to represent diverse topologies. However, neural implicit representations are limited to closed surfaces, which divide the space into inside and outside. Many real world objects such as walls of a scene scanned by a sensor, clothing, or a car with inner structures are not closed. This constitutes a significant barrier, in terms of data pre-processing (objects need to be artificially closed creating artifacts), and the ability to output open surfaces. In this work, we propose Neural Distance Fields (NDF), a neural network based model which predicts the unsigned distance field for arbitrary 3D shapes given sparse point clouds. NDF represent surfaces at high resolutions as prior implicit models, but do not require closed surface data, and significantly broaden the class of representable shapes in the output. NDF allow to extract the surface as very dense point clouds and as meshes. We also show that NDF allow for surface normal calculation and can be rendered using a slight modification of sphere tracing. We find NDF can be used for multi-target regression (multiple outputs for one input) with techniques that have been exclusively used for rendering in graphics. Experiments on ShapeNet show that NDF, while simple, is the state-of-the art, and allows to reconstruct shapes with inner structures, such as the chairs inside a bus. Notably, we show that NDF are not restricted to 3D shapes, and can approximate more general open surfaces such as curves, manifolds, and functions. Code is available for research at https://virtualhumans.mpi-inf.mpg.de/ndf/., Comment: Neural Information Processing Systems (NeurIPS) 2020

Implicit functions represented as deep learning approximations are powerful for reconstructing 3D surfaces. However, they can only produce static surfaces that are not controllable, which provides limited ability to modify the resulting model by editing its pose or shape parameters. Nevertheless, such features are essential in building flexible models for both computer graphics and computer vision. In this work, we present methodology that combines detail-rich implicit functions and parametric representations in order to reconstruct 3D models of people that remain controllable and accurate even in the presence of clothing. Given sparse 3D point clouds sampled on the surface of a dressed person, we use an Implicit Part Network (IP-Net)to jointly predict the outer 3D surface of the dressed person, the and inner body surface, and the semantic correspondences to a parametric body model. We subsequently use correspondences to fit the body model to our inner surface and then non-rigidly deform it (under a parametric body + displacement model) to the outer surface in order to capture garment, face and hair detail. In quantitative and qualitative experiments with both full body data and hand scans we show that the proposed methodology generalizes, and is effective even given incomplete point clouds collected from single-view depth images. Our models and code can be downloaded from http://virtualhumans.mpi-inf.mpg.de/ipnet.