activity
20192022
most citedEVA3D: Compositional 3D Human Generation from 2D Image Collections

36 citations · 62 across the 7 of their papers we have counts for

collaborators

10 papers

cs.CV202236 cited

EVA3D: Compositional 3D Human Generation from 2D Image Collections

Fangzhou Hong, Zhaoxi Chen, Yushi Lan +2

Inverse graphics aims to recover 3D models from 2D observations. Utilizing differentiable rendering, recent 3D-aware generative models have shown impressive results of rigid object…

cs.CV202219 cited

AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars

Fangzhou Hong, Mingyuan Zhang, Liang Pan +3

3D avatar creation plays a crucial role in the digital age. However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technolog…

cs.CV20222 cited

TCTrack: Temporal Contexts for Aerial Tracking

Ziang Cao, Ziyuan Huang, Liang Pan +3

Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack, a comprehensive framework to fully explo…

cs.CV20221 cited

Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture

Buzhen Huang, Liang Pan, Yuan Yang +2

Due to the visual ambiguity, purely kinematic formulations on monocular human motion capture are often physically incorrect, biomechanically implausible, and can not reconstruct ac…

cs.CV2022

Versatile Multi-Modal Pre-Training for Human-Centric Perception

Fangzhou Hong, Liang Pan, Zhongang Cai +1

Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train…

cs.CV2021

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Daxuan Ren, Jianmin Zheng, Jianfei Cai +8

Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem. This paper presents CSG-Stump Net, an unsupervised en…