From the 1 of 6 linked papers with an AI index.
6 papers
RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration
Jiahao Luo, Hao Zhang, Jianqi Chen +9
RegHead is a framework that builds semantic blendshape sets for animatable non‑humanoid head avatars using a fast feed‑forward registration model and a large dataset of shared expr…
MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequences
Jianqi Chen, Jiraphon Yenphraphai, Xiangjun Tang +4
We present MeshLoom, a feed-forward registration network that directly reconstructs vertex deformations across mesh sequences. Our approach advances non-rigid registration beyond e…
PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
Jianqi Chen, Biao Zhang, Xiangjun Tang +1
6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on expl…
Helix4D: Complex 4D Mesh Generation
Jiraphon Yenphraphai, Jianqi Chen, Jian Wang +6
Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic mesh generation framew…
ShapeGen4D: Towards High Quality 4D Shape Generation from Videos
Jiraphon Yenphraphai, Ashkan Mirzaei, Jianqi Chen +5
Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native vide…
V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video
Jianqi Chen, Biao Zhang, Xiangjun Tang +1
We present V2M4, a novel 4D reconstruction method that directly generates a usable 4D mesh animation asset from a single monocular video. Unlike existing approaches that rely on pr…