State of the art on diffusion models for visual computing
The field of visual computing is rapidly advancing due to the emergence of generative
artificial intelligence (AI), which unlocks unprecedented capabilities for the generation …
artificial intelligence (AI), which unlocks unprecedented capabilities for the generation …
Hugs: Human gaussian splats
Recent advances in neural rendering have improved both training and rendering times by
orders of magnitude. While these methods demonstrate state-of-the-art quality and speed …
orders of magnitude. While these methods demonstrate state-of-the-art quality and speed …
Interdiff: Generating 3d human-object interactions with physics-informed diffusion
This paper addresses a novel task of anticipating 3D human-object interactions (HOIs). Most
existing research on HOI synthesis lacks comprehensive whole-body interactions with …
existing research on HOI synthesis lacks comprehensive whole-body interactions with …
Effective whole-body pose estimation with two-stages distillation
Whole-body pose estimation localizes the human body, hand, face, and foot keypoints in an
image. This task is challenging due to multi-scale body parts, fine-grained localization for …
image. This task is challenging due to multi-scale body parts, fine-grained localization for …
3D human pose estimation via intuitive physics
Estimating 3D humans from images often produces implausible bodies that lean, float, or
penetrate the floor. Such methods ignore the fact that bodies are typically supported by the …
penetrate the floor. Such methods ignore the fact that bodies are typically supported by the …
Smpler-x: Scaling up expressive human pose and shape estimation
Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion
capture with numerous applications. Despite encouraging progress, current state-of-the-art …
capture with numerous applications. Despite encouraging progress, current state-of-the-art …
Object motion guided human motion synthesis
Modeling human behaviors in contextual environments has a wide range of applications in
character animation, embodied AI, VR/AR, and robotics. In real-world scenarios, humans …
character animation, embodied AI, VR/AR, and robotics. In real-world scenarios, humans …
Diffusion-guided reconstruction of everyday hand-object interaction clips
Y Ye, P Hebbar, A Gupta… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We tackle the task of reconstructing hand-object interactions from short video clips. Given an
input video, our approach casts 3D inference as a per-video optimization and recovers a …
input video, our approach casts 3D inference as a per-video optimization and recovers a …
Hi4d: 4d instance segmentation of close human interaction
We propose Hi4D, a method and dataset for the auto analysis of physically close human-
human interaction under prolonged contact. Robustly disentangling several in-contact …
human interaction under prolonged contact. Robustly disentangling several in-contact …
A dataset of relighted 3D interacting hands
The two-hand interaction is one of the most challenging signals to analyze due to the self-
similarity, complicated articulations, and occlusions of hands. Although several datasets …
similarity, complicated articulations, and occlusions of hands. Although several datasets …