3D Vision

FastAvatar: Towards Unified Fast High-Fidelity 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers

The paper proposes FastAvatar, a unified, feedforward framework that reconstructs high-quality 3D avatars in seconds from single images, videos, or multi-view inputs. With …

Yue Wu

• Aug 1, 2025 • 1 min read

3D Vision

SinGS: Animatable Single-Image Human Gaussian Splats with Kinematic Priors

The Paper presents SinGS, a framework for efficient and high-quality animatable 3D human reconstruction from a single image. It integrates Kinematic Human Diffusion to infer unseen …

Yufan Wu

• Jul 1, 2025 • 1 min read