SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration
This addresses the need for efficient and detailed 3D reconstruction in computer vision, though it appears incremental as it builds on existing neural SDF and multi-view methods.
The paper tackles the problem of fast, high-fidelity 3D surface reconstruction from multi-view images by using surface normal maps, achieving results comparable to 3D scanners in a few minutes with nearly twice the efficiency of analytical gradients and about three times faster than axis-aligned finite difference.
We present SuperNormal, a fast, high-fidelity approach to multi-view 3D reconstruction using surface normal maps. With a few minutes, SuperNormal produces detailed surfaces on par with 3D scanners. We harness volume rendering to optimize a neural signed distance function (SDF) powered by multi-resolution hash encoding. To accelerate training, we propose directional finite difference and patch-based ray marching to approximate the SDF gradients numerically. While not compromising reconstruction quality, this strategy is nearly twice as efficient as analytical gradients and about three times faster than axis-aligned finite difference. Experiments on the benchmark dataset demonstrate the superiority of SuperNormal in efficiency and accuracy compared to existing multi-view photometric stereo methods. On our captured objects, SuperNormal produces more fine-grained geometry than recent neural 3D reconstruction methods.