Search Results for author:
Found 5 papers, 2 papers with code
CaPa: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation
In this paper, we introduce \textbf{CaPa}, a carve-and-paint framework that generates high-fidelity 3D assets efficiently.
Transformer-Based Unified Recognition of Two Hands Manipulating Objects
In our framework, we insert the whole image depicting two hands, an object and their interactions as input and jointly estimate 3 information from each frame: poses of two hands, pose of an object and object types.
Ranked #4 on
Action Recognition
on H2O (2 Hands and Objects)
HOReeNet: 3D-aware Hand-Object Grasping Reenactment
At the same time, to obtain high-quality 2D images from 3D space, well-designed 3D-to-2D projection and image refinement are required.
Image-free Domain Generalization via CLIP for 3D Hand Pose Estimation
The manipulated image features are then exploited to train the hand pose estimation network via the contrastive learning framework.
Transformer-based Global 3D Hand Pose Estimation in Two Hands Manipulating Objects Scenarios
In this challenge, we aim to estimate global 3D hand poses from the input image where two hands and an object are interacting on the egocentric viewpoint.
