AI Paper Atlas

Research map / 3D vision / Depth and stereo

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

Xi Chen, Jiaming Sun, Yiming Xie, Hujun Bao, Xiaowei Zhou

TPAMI 2024 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 17 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-level averaging fusion in place of linear TSDF fusion (ablation)NeuralRecon · ScanNet (Atlas split)precision: 0.386 -> 0.432Improved
add feature-level averaging fusion in place of linear TSDF fusion (ablation)NeuralRecon · ScanNet (Atlas split)F-score: 0.462 -> 0.478Improved
replace average fusion with GRU fusion (ablation)NeuralRecon · ScanNet (Atlas split)recall: 0.535 -> 0.572Improved
replace average fusion with GRU fusion (ablation)NeuralRecon · ScanNet (Atlas split)F-score: 0.478 -> 0.488Improved
fuse within fragment bounding volume instead of occupied area only (ablation)NeuralRecon with GRU · ScanNet (Atlas split)recall: 0.572 -> 0.613Improved
fuse within fragment bounding volume instead of occupied area only (ablation)NeuralRecon with GRU · ScanNet (Atlas split)F-score: 0.488 -> 0.494Improved
increase fragment length from 5 to 9 views (ablation)NeuralRecon · ScanNet (Atlas split)F-score: 0.494 -> 0.516Improved
increase fragment length from 9 to 11 views (ablation)NeuralRecon · ScanNet (Atlas split)F-score: 0.516 -> 0.474Hurt
increase fragment length from 5 to 7 views (ablation)NeuralRecon · ScanNet (Atlas split)F-score: 0.494 -> 0.507Improved
use NeuralRecon volumetric fragment reconstruction instead of AtlasScanNet reconstruction · ScanNet (Atlas split, double-layer)time per key frame (ms): 292 -> 30Improved
use NeuralRecon instead of AtlasScanNet reconstruction · ScanNet (Atlas split, double-layer)F-score: 0.499 -> 0.516Improved
use NeuralRecon instead of AtlasScanNet reconstruction · ScanNet (Atlas split, double-layer)recall: 0.732 -> 0.609Hurt

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