Papers › MVSNet: Depth Inference for Unstructured Multi-view Stereo

MVSNet: Depth Inference for Unstructured Multi-view Stereo

7 Apr 2018ECCV 2018 9arXiv:1804.02505archive 2025-07-28

Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, Long Quan

We present an end-to-end deep learning architecture for depth map inference from multi-view images. In the network, we first extract deep visual image features, and then build the 3D cost volume upon the reference camera frustum via the differentiable homography warping. Next, we apply 3D convolutions to regularize and regress the initial depth map, which is then refined with the reference image to generate the final output. Our framework flexibly adapts arbitrary N-view inputs using a variance-based cost metric that maps multiple features into one cost feature. The proposed MVSNet is demonstrated on the large-scale indoor DTU dataset. With simple post-processing, our method not only significantly outperforms previous state-of-the-arts, but also is several times faster in runtime. We also evaluate MVSNet on the complex outdoor Tanks and Temples dataset, where our method ranks first before April 18, 2018 without any fine-tuning, showing the strong generalization ability of MVSNet.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Skoltech-3D/sk3d_data mentioned on GitHubNOASSERTIONSyntology: not harvested report
YoYo000/MVSNet mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference (arXiv:1902.10556; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
kwea123/MVSNet_pl mentioned on GitHubpytorchSyntology: not harvested report
xy-guo/MVSNet_pytorch mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-213 mindsporeSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D ReconstructionPoint Clouds

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Reconstruction DTU MVSNet Acc 0.396 #21 of 24 Archive leaderboard report
3D Reconstruction DTU MVSNet Comp 0.527 #21 of 24 Archive leaderboard report
3D Reconstruction DTU MVSNet Overall 0.462 #21 of 24 Archive leaderboard report
Point Clouds Tanks and Temples MVSNet Mean F1 (Intermediate) 43.48 #21 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections