RGBD-to-3D Object Mesh Refinement via Depth Matching and Symmetry Propagation

arXiv:2610.11187 · cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Comments: To be appear in ACCV2026

Project page: https://ahyunseo.github.io/MatchPropMesh

License: http://creativecommons.org/licenses/by/4.0/

The gist: Single-view 3D reconstructors often produce plausible meshes that disagree with the input view, especially near depth discontinuities and self-occlusions.

Terminology

Abstract

Single-view 3D reconstructors often produce plausible meshes that disagree with the input view, especially near depth discontinuities and self-occlusions. We present a lightweight, plug-and-play RGBD-to-3D refinement that improves any RGB-to-3D reconstructor without retraining. Given a depth map, we correct the visible surface by bipartite matching to back-projected depth points, mirror these corrections onto the occluded side across a detected symmetry plane, and propagate them with a smoothness solver. Every stage is closed-form, making the method orders of magnitude faster than optimization-heavy test-time refinement. On GSO and OmniObject3D with five backbones, it yields consistent gains, also with monocular pseudo-depth, benefits more from symmetry on symmetric objects, and compares favorably with prior refinement in accuracy and runtime. It further improves an RGB-D-to-mesh reconstructor and transfers to real captures with noisy sensor depth.

Sources

Related papers