2 citations · 8 across the 6 of their papers we have counts for
5 papers · 1 filter
Steering Video Diffusion Transformers with Massive Activations
Xianhang Cheng, Yujian Zheng, Zhenyu Xie +2
In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude spikes confined to a few fixed hidden dimensions in video diffusion transformers (DiTs)…
SOAP: Style-Omniscient Animatable Portraits
Tingting Liao, Yujian Zheng, Adilbek Karmanov +4
Creating animatable 3D avatars from a single image remains challenging due to style limitations (realistic, cartoon, anime) and difficulties in handling accessories or hairstyles.…
TeCH: Text-guided Reconstruction of Lifelike Clothed Humans
Yangyi Huang, Hongwei Yi, Yuliang Xiu +4
Despite recent research advancements in reconstructing clothed humans from a single image, accurately restoring the "unseen regions" with high-level details remains an unsolved cha…
High-Fidelity Clothed Avatar Reconstruction from a Single Image
Tingting Liao, Xiaomei Zhang, Yuliang Xiu +7
This paper presents a framework for efficient 3D clothed avatar reconstruction. By combining the advantages of the high accuracy of optimization-based methods and the efficiency of…
MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames
Xiangyu Zhu, Tingting Liao, Jiangjing Lyu +6
In this paper, we consider a novel problem of reconstructing a 3D human avatar from multiple unconstrained frames, independent of assumptions on camera calibration, capture space,…