4 papers · 1 filter
A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics
Hao-Jen Chien, Wei-Lun Chao, Yu-Lun Liu
Monocular world-space human recovery methods excel on current benchmarks, but these rarely include fast camera motion. We introduce the K-Pop stress test, broadcast dance videos th…
Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting
Hao-Jen Chien, Yi-Chuan Huang, Chung-Ho Wu +2
Synthesizing high-fidelity frozen 3D scenes from monocular Mannequin-Challenge (MC) videos is a unique problem distinct from standard dynamic scene reconstruction. Instead of focus…
GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
Yi-Chuan Huang, Hao-Jen Chien, Chin-Yang Lin +2
Recent 3D reconstruction methods achieve impressive results with dense multi-view imagery but struggle when only a few views are available. Various approaches, including regulariza…
Voxify3D: Pixel Art Meets Volumetric Rendering
Yi-Chuan Huang, Jiewen Chan, Hao-Jen Chien +1
Voxel art is a distinctive stylization widely used in games and digital media, yet automated generation from 3D meshes remains challenging due to conflicting requirements of geomet…