14 papers
UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
Haiyang Zhou, Wangbo Yu, Chaoran Feng +3
The abundance of casually captured monocular videos and images on social media provides a valuable source for immersive content creation, where generating novel views from such spa…
MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction
Dehao Hao, Kaiyi Zhang, Tanghui Jia +10
High-fidelity 3D generative modeling increasingly relies on the latent diffusion paradigm, where the reconstruction quality of the underlying 3D VAE becomes a primary bottleneck. E…
AnyAct: Towards Human Reenactment of Character Motion From Video
Liuhan Chen, Lei Zhong, Jiawei Wang +6
We study the problem of directly deriving an initial human reenactment from a monocular video of a non-human character. Our goal is not to reconstruct the source character itself b…
DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images
Changyue Shi, Wangbo Yu, Chaoran Feng +1
Novel view synthesis (NVS) is a fundamental problem in computer vision and graphics. Recent advances in neural radiance fields (NeRF), 3D Gaussian Splatting (3DGS), and generative…
Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Views
Zhankuo Xu, Chaoran Feng, Yingtao Li +5
3D Gaussian Splatting (3DGS) has emerged as a state-of-the-art method for novel view synthesis. However, its performance heavily relies on dense, high-quality input imagery, an ass…
UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
Tanghui Jia, Dongyu Yan, Dehao Hao +11
In this report, we introduce UltraShape 1.0, a scalable 3D diffusion framework for high-fidelity 3D geometry generation. The proposed approach adopts a two-stage generation pipelin…