Related papers: PhysiGen: Integrating Collision-Aware Physical Con…

Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, recent methods achieve high performance in depth estimation from a single image. Meanwhile,…

In recent years, autonomous driving has significantly in creased the demand for high-quality data to train 2D and 3D perception models for safety-critical scenarios. Real world datasets struggle to meet this demand as require ments…

Collision avoidance -- involving a rapid threat detection and quick execution of the appropriate evasive maneuver -- is a critical aspect of driving. However, existing models of human collision avoidance behavior are fragmented, focusing on…

Traditional motion planning approaches for multi-legged locomotion divide the problem into several stages, such as contact search and trajectory generation. However, reasoning about contacts and motions simultaneously is crucial for the…

Human motion synthesis conditioned on textual input has gained significant attention in recent years due to its potential applications in various domains such as gaming, film production, and virtual reality. Conditioned Motion synthesis…

Dexterous grasp synthesis must jointly satisfy functional intent and physical feasibility, yet existing pipelines often decouple semantic grounding from refinement, yielding unstable or non-functional contacts under object and pose…

Generating intelligent robot behavior in contact-rich settings is a research problem where zeroth-order methods currently prevail. A major contributor to the success of such methods is their robustness in the face of non-smooth and…

Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition…

Recent advances in 3D-aware GAN models have enabled the generation of realistic and controllable human body images. However, existing methods focus on the control of major body joints, neglecting the manipulation of expressive attributes,…

Humanoid motion control has witnessed significant breakthroughs in recent years, with deep reinforcement learning (RL) emerging as a primary catalyst for achieving complex, human-like behaviors. However, the high dimensionality and…

Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle…

Existing multi-person human reconstruction approaches mainly focus on recovering accurate poses or avoiding penetration, but overlook the modeling of close interactions. In this work, we tackle the task of reconstructing closely interactive…

Real-world human-built environments are highly dynamic, involving multiple humans and their complex interactions with surrounding objects. While 3D geometry modeling of such scenes is crucial for applications like AR/VR, gaming, and…

Synthesizing 3D human avatars interacting realistically with a scene is an important problem with applications in AR/VR, video games and robotics. Towards this goal, we address the task of generating a virtual human -- hands and full body…

Existing 3D human mesh recovery methods often fail to fully exploit the latent information (e.g., human motion, shape alignment), leading to issues with limb misalignment and insufficient local details in the reconstructed human mesh…

Existing image-based virtual try-on methods are often limited to the front view and lack real-time performance. While per-garment virtual try-on methods have tackled these issues by capturing per-garment datasets and training per-garment…

We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions (e.g., applied force and torque), producing…

The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discussed. In this paper, we propose an end-to-end learning strategy…

Recent advances in deep learning have enabled the generation of videos from textual descriptions as well as the prediction of future sequences from input videos. Similarly, in human motion modeling, motions can be generated from text or…

Human interactions in everyday life are inherently social, involving engagements with diverse individuals across various contexts. Modeling these social interactions is fundamental to a wide range of real-world applications. In this paper,…