Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images
Atsuhiro Noguchi, Tianhan Xu, Yiming Liang +5
We reconstruct high-fidelity 3D scene meshes from posed multi-view images without per-scene optimization, across scales ranging from single objects to large outdoor scenes. Per-sce…
cs.CV2025
HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation
Yiming Liang, Tianhan Xu, Yuta Kikuchi
We present Hierarchical Motion Representation (HiMoR), a novel deformation representation for 3D Gaussian primitives capable of achieving high-quality monocular dynamic 3D reconstr…