AI Paper Atlas

Research map / 3D vision / Depth and stereo

NeuralRecon: Real-Time Coherent 3D Reconstruction From Monocular Video

CVPR 2021 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 313 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
jointly reconstruct local fragments and fuse their TSDFs with GRUNeuralRecon · ScanNet (Atlas split, single-layer)F-scoreHelped
replace conventional linear TSDF fusion with average feature fusion (ablation)NeuralRecon · ScanNet, 5 views, OCC fusionPrecision: 0.386 -> 0.432Helped
replace average feature fusion with GRU fusion (ablation)NeuralRecon · ScanNet, 5 views, OCC fusionRecall: 0.535 -> 0.572Helped
fuse GRU features within the fragment bounding volume instead of the occupied area (ablation)NeuralRecon · ScanNet, 5 viewsRecall: 0.572 -> 0.613Helped
increase fragment length from 5 to 7 views (ablation)NeuralRecon · ScanNet, FBV fusionF-score: 0.494 -> 0.507Helped
increase fragment length from 5 to 9 views (ablation)NeuralRecon · ScanNet, FBV fusionF-score: 0.494 -> 0.516Helped
increase fragment length from 5 to 11 views (ablation)NeuralRecon · ScanNet, FBV fusionF-score: 0.494 -> 0.474Hurt

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