发表机构
POSTECH; KAIST（浦项科技大学; 韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种轻量即插即用的RGBD到3D网格细化方法，通过深度匹配与对称性传播实现，无需重训练即可改进各类RGB到3D重建器，在多数据集及真实数据上均取得精度与效率优势。
AI 中文摘要
单视图3D重建器常生成与输入视图不一致的合理网格，尤其在深度不连续处和自遮挡区域。本文提出一种轻量、即插即用的RGBD到3D细化方法，无需重新训练即可改进任何RGB到3D重建器。给定深度图，通过与反投影深度点的二分匹配修正可见表面，在检测到的对称平面上将这些修正镜像到遮挡侧，并通过平滑求解器传播。每个阶段均为闭式解，使该方法比重优化的测试时细化快几个数量级。在GSO和OmniObject3D数据集上，使用五种骨干网络时，该方法取得一致提升，对单目伪深度同样有效，对对称物体从对称性中获益更多，在精度和运行时间上优于现有细化方法。它还改进了RGBD到网格重建器，并可迁移到含噪声传感器深度的真实采集数据。
英文摘要
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.
CommentsTo be appear in ACCV2026
