1 citations · 1 across the 4 of their papers we have counts for
5 papers
Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images
Jianchuan Chen, Wentao Yi, Tiantian Wang +4
In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric p…
Controllable Radiance Fields for Dynamic Face Synthesis
Peiye Zhuang, Liqian Ma, Oluwasanmi Koyejo +1
Recent work on 3D-aware image synthesis has achieved compelling results using advances in neural rendering. However, 3D-aware synthesis of face dynamics hasn't received much attent…
FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty
Liqian Ma, Stamatios Georgoulis, Xu Jia +1
The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and ro…
Direct Dense Pose Estimation
Liqian Ma, Lingjie Liu, Christian Theobalt +1
Dense human pose estimation is the problem of learning dense correspondences between RGB images and the surfaces of human bodies, which finds various applications, such as human bo…
Appearance Harmonization for Single Image Shadow Removal
Liqian Ma, Jue Wang, Eli Shechtman +2
Shadows often create unwanted artifacts in photographs, and removing them can be very challenging. Previous shadow removal methods often produce de-shadowed regions that are visual…