Unstructured Multi-View Depth Estimation Using Mask-Based Multiplane Representation
This addresses depth estimation for computer vision applications, offering a lightweight and generalizable solution, though it appears incremental as it builds on plane-sweep methods.
The paper tackles depth estimation from unstructured multi-view images by introducing MaskMVS, a method that uses a multiplane mask representation to regularize learning without explicit cost volume construction, achieving state-of-the-art results on datasets like sun3d and MVS.
This paper presents a novel method, MaskMVS, to solve depth estimation for unstructured multi-view image-pose pairs. In the plane-sweep procedure, the depth planes are sampled by histogram matching that ensures covering the depth range of interest. Unlike other plane-sweep methods, we do not rely on a cost metric to explicitly build the cost volume, but instead infer a multiplane mask representation which regularizes the learning. Compared to many previous approaches, we show that our method is lightweight and generalizes well without requiring excessive training. We outperform the current state-of-the-art and show results on the sun3d, scenes11, MVS, and RGBD test data sets.