SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.09722 · 2020

M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The present Multi-view stereo (MVS) methods with supervised learning-based networks have an impressive performance comparing with traditional MVS methods. However, the ground-truth depth maps for training are hard to be obtained and are within limited kinds of scenarios. In this paper, we propose a novel unsupervised multi-metric MVS network, named M^3VSNet, for dense point cloud reconstruction without any supervision. To improve the robustness and completeness of point cloud reconstruction, we propose a novel multi-metric loss function that combines pixel-wise and feature-wise loss function to learn the inherent constraints from different perspectives of matching correspondences. Besides, we also incorporate the normal-depth consistency in the 3D point cloud format to improve the accuracy and continuity of the estimated depth maps. Experimental results show that M3VSNet establishes the state-of-the-arts unsupervised method and achieves comparable performance with previous supervised MVSNet on the DTU dataset and demonstrates the powerful generalization ability on the Tanks and Temples benchmark with effective improvement. Our code is available at https://github.com/whubaichuan/M3VSNet.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2004.09722")
get_code_for_paper("2004.09722")
have("2004.09722")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2004.09722.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2004.09722.svg)](https://syntology.ai/paper/2004.09722)

Connect an agent — have() is free.