CVGRApr 4, 2024

Discontinuity-preserving Normal Integration with Auxiliary Edges

arXiv:2404.03138v14 citationsh-index: 5CVPR
Originality Incremental advance
AI Analysis

This work addresses a specific challenge in surface reconstruction for computer vision and graphics, offering an incremental improvement over existing discontinuity-preserving normal integration techniques.

The paper tackles the problem of reconstructing accurate depth maps from normal maps with discontinuities, such as those from self-occlusion, by introducing auxiliary edges to explicitly model hidden jumps, resulting in more accurate reconstruction of subtle discontinuities compared to previous methods.

Many surface reconstruction methods incorporate normal integration, which is a process to obtain a depth map from surface gradients. In this process, the input may represent a surface with discontinuities, e.g., due to self-occlusion. To reconstruct an accurate depth map from the input normal map, hidden surface gradients occurring from the jumps must be handled. To model these jumps correctly, we design a novel discretization scheme for the domain of normal integration. Our key idea is to introduce auxiliary edges, which bridge between piecewise-smooth patches in the domain so that the magnitude of hidden jumps can be explicitly expressed. Using the auxiliary edges, we design a novel algorithm to optimize the discontinuity and the depth map from the input normal map. Our method optimizes discontinuities by using a combination of iterative re-weighted least squares and iterative filtering of the jump magnitudes on auxiliary edges to provide strong sparsity regularization. Compared to previous discontinuity-preserving normal integration methods, which model the magnitudes of jumps only implicitly, our method reconstructs subtle discontinuities accurately thanks to our explicit representation of jumps allowing for strong sparsity regularization.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes