Learning Signed Distance Field for Multi-View Surface Reconstruction

Jingyang Zhang, Yao Yao, Long Quan; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 6525-6534


Recent works on implicit neural representations have shown promising results for multi-view surface reconstruction. However, most approaches are limited to relatively simple geometries and usually require clean object masks for reconstructing complex and concave objects. In this work, we introduce a novel neural surface reconstruction framework that leverages the knowledge of stereo matching and feature consistency to optimize the implicit surface representation. More specifically, we apply a signed distance field (SDF) and a surface light field to represent the scene geometry and appearance respectively. The SDF is directly supervised by geometry from stereo matching, and is refined by optimizing the multi-view feature consistency and the fidelity of rendered images. Our method is able to improve the robustness of geometry estimation and support reconstruction of complex scene topologies. Extensive experiments have been conducted on DTU, EPFL and Tanks and Temples datasets. Compared to previous state-of-the-art methods, our method achieves better mesh reconstruction in wide open scenes without masks as input.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Zhang_2021_ICCV, author = {Zhang, Jingyang and Yao, Yao and Quan, Long}, title = {Learning Signed Distance Field for Multi-View Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {6525-6534} }