# Unstructured Multi-View Depth Estimation Using Mask-Based Multiplane Representation

## TL;DR

This paper introduces MaskMVS, a lightweight and generalizable unstructured multi-view depth estimation method that uses a novel multiplane mask representation instead of traditional cost volume approaches, achieving state-of-the-art results.

## Contribution

The paper proposes a new multiplane mask representation for depth estimation that avoids explicit cost volume construction, improving efficiency and generalization.

## Key findings

- Outperforms current state-of-the-art on multiple datasets
- Lightweight and does not require extensive training
- Generalizes well across different data sets

## Abstract

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.