AI Paper Atlas

Research map / 3D vision / Depth and stereo

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

Di Chang, Aljaž Božič, Tong Zhang, Qingsong Yan, Yingcong Chen, Sabine Süsstrunk, Matthias Nießner

ECCV 2022 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 68 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add data augmentation loss L_DA (ablation)RC-MVSNet baseline · DTUOverall: 0.395 -> 0.383Improved
add reference view synthesis loss L_RC (ablation)RC-MVSNet · DTUOverall: 0.383 -> 0.357Improved
add Gaussian-Uniform mixture sampling (ablation)RC-MVSNet with L_RC · DTUOverall: 0.357 -> 0.352Improved
add depth rendering consistency loss L_DC (ablation)RC-MVSNet with L_RC · DTUOverall: 0.357 -> 0.348Improved
add L_DC on top of Gaussian-Uniform sampling (ablation)RC-MVSNet · DTUOverall: 0.352 -> 0.345Improved
increase sampled rays from 256 to 1024, 4096, 8192 (ablation)RC-MVSNet · DTUOverall: 0.350 -> 0.345 (1024), 0.350 (4096), 0.348 (8192)No clear effect
RC-MVSNet instead of JDACS-MSunsupervised E2E MVS · DTUOverall: 0.358 -> 0.345Improved
RC-MVSNet instead of JDACS-MSunsupervised E2E MVS · DTUCompleteness: 0.318 -> 0.295Improved
RC-MVSNet instead of M3VSNetunsupervised E2E MVS · Tanks and Temples intermediatemean F-score: +17.37Improved
RC-MVSNet instead of JDACS-MSunsupervised E2E MVS · Tanks and Temples intermediatemean F-score: 45.48 -> 55.04Improved

Later papers that compared with this method

3 later accepted papers report RC-MVSNet as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy