AI Paper Atlas

Research map / 3D vision / Depth and stereo

SimpleRecon: 3D Reconstruction without 3D Convolutions

Mohamed Sayed, John Gibson, Jamie Watson, Victor Prisacariu, Michael Firman, Clément Godard

ECCV 2022 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 104 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 feature, mask and depth metadata to the cost volume MLP (ablation)SimpleRecon baseline · ScanNetv2 ablationAbs Diff: 0.0941 -> 0.0904Improved
add ray and angle metadata (ablation)SimpleRecon · ScanNetv2 ablationAbs Diff: 0.0904 -> 0.0896Improved
add pose distance metadata (ablation)SimpleRecon · ScanNetv2 ablationAbs Diff: 0.0896 -> 0.0885Improved
add all metadata to the MLP cost volume (ablation)SimpleRecon baseline · ScanNetv2 mesh evalF-score: 64.2 -> 67.1Improved
use 64 feature channels instead of 16 in the dot product cost volume (ablation)SimpleRecon baseline · ScanNetv2 ablationAbs Diff: 0.0941 -> 0.0944Hurt
order keyframes by pose distance instead of shuffling (with metadata) (ablation)SimpleRecon · ScanNetv2 ablationAbs Diff: 0.0906 -> 0.0885Improved
increase source views from 1 (no CV) to 2 (ablation)SimpleRecon · ScanNetv2 ablationAbs Diff: 0.1742 -> 0.1230Improved
increase source views from 2 to 4 (ablation)SimpleRecon · ScanNetv2 ablationAbs Diff: 0.1230 -> 0.1036Improved
increase source views from 4 to 8 (ablation)SimpleRecon · ScanNetv2 ablationAbs Diff: 0.1036 -> 0.0885Improved
use EfficientNetV2 S + R18 backbone instead of MnasNet at 320x256 (ablation)SimpleRecon · ScanNetv2 ablationAbs Diff: 0.0947 -> 0.0885Improved
use SimpleRecon 2D CNN with TSDF fusion instead of 3D CNN update methodsSimpleRecon · Frame integration latencyupdate latency (ms): 382ms -> 72msImproved
use SimpleRecon instead of DeepVideoMVS fusiondepth estimation · ScanNetv2 depthAbs Diff: 0.1186 -> 0.0885Improved

Later papers that compared with this method

9 later accepted papers report SimpleRecon as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

1 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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