Related papers: Synthesizing Long-Term 3D Human Motion and Interac…
Synthesizing photo-realistic images and videos is at the heart of computer graphics and has been the focus of decades of research. Traditionally, synthetic images of a scene are generated using rendering algorithms such as rasterization or…
Demystifying complex human-ground interactions is essential for accurate and realistic 3D human motion reconstruction from RGB videos, as it ensures consistency between the humans and the ground plane. Prior methods have modeled…
We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photorealistic images of full-body humans with consistent appearances under different view-angles and body-poses. To tackle the representational and…
Recent works on dynamic 3D neural field reconstruction assume the input from synchronized multi-view videos whose poses are known. The input constraints are often not satisfied in real-world setups, making the approach impractical. We show…
Prompt-driven scene synthesis allows users to generate complete 3D environments from textual descriptions. Current text-to-scene methods often struggle with complex geometries and object transformations, and tend to show weak adherence to…
This report surveys advances in deep learning-based modeling techniques that address four different 3D indoor scene analysis tasks, as well as synthesis of 3D indoor scenes. We describe different kinds of representations for indoor scenes,…
Recent progress on physics-based character animation has shown impressive breakthroughs on human motion synthesis, through imitating motion capture data via deep reinforcement learning. However, results have mostly been demonstrated on…
We present a novel method to generate human motion to populate 3D indoor scenes. It can be controlled with various combinations of conditioning signals such as a path in a scene, target poses, past motions, and scenes represented as 3D…
To understand and analyze human behavior, we need to capture humans moving in, and interacting with, the world. Most existing methods perform 3D human pose estimation without explicitly considering the scene. We observe however that the…
The connection between our 3D surroundings and the descriptive language that characterizes them would be well-suited for localizing and generating human motion in context but for one problem. The complexity introduced by multiple modalities…
We present a novel framework for animating humans in 3D scenes using 3D Gaussian Splatting (3DGS), a neural scene representation that has recently achieved state-of-the-art photorealistic results for novel-view synthesis but remains…
Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face several challenges in generating long videos with rich human-scene interactions (HSI),…
Human motion generation has advanced rapidly in recent years, yet the critical problem of creating spatially grounded, context-aware gestures has been largely overlooked. Existing models typically specialize either in descriptive motion…
The concept of function and affordance is a critical aspect of 3D scene understanding and supports task-oriented objectives. In this work, we develop a model that learns to structure and vary functional affordance across a 3D hierarchical…
We study the problem of synthesizing immersive 3D indoor scenes from one or more images. Our aim is to generate high-resolution images and videos from novel viewpoints, including viewpoints that extrapolate far beyond the input images while…
Estimating the geometry level of human-scene contact aims to ground specific contact surface points at 3D human geometries, which provides a spatial prior and bridges the interaction between human and scene, supporting applications such as…
3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent…
Robotic grasping of house-hold objects has made remarkable progress in recent years. Yet, human grasps are still difficult to synthesize realistically. There are several key reasons: (1) the human hand has many degrees of freedom (more than…
Human motion prediction is consisting in forecasting future body poses from historically observed sequences. It is a longstanding challenge due to motion's complex dynamics and uncertainty. Existing methods focus on building up complicated…
Despite substantial progress in text-driven 3D human motion synthesis, generating realistic multi-person interaction sequences remains challenging. Notably, body inter-penetration is a pervasive issue from both data acquisition to the…