AI Paper Atlas

Research map / 3D vision / Face and shape

FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction

Noah Stier, Anurag Ranjan, Alex Colburn, Yajie Yan, Liang Yang, Fangchang Ma, Baptiste Angles

ICCV 2023 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 33 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
supervise TSDF only at exact ground-truth points instead of interpolated voxel centers (resolution-agnostic supervision) (ablation)FineRecon · ScanNet testChamfer distance: 6.40 -> 5.58Improved
add depth guidance via fused MVS TSDF channel (ablation)FineRecon · ScanNet testChamfer distance: 5.58 -> 5.25Improved
add point back-projection when depth guidance is on (ablation)FineRecon · ScanNet testChamfer distance: 5.25 -> 5.18Improved
add point back-projection without depth guidance (ablation)FineRecon · ScanNet testChamfer distance: 5.58 -> 5.80Hurt
use TSDF fusion depth guidance instead of density volume (ablation)FineRecon · ScanNet testF1: 74.3 -> 75.5Improved
use TSDF fusion depth guidance instead of Gaussian weighting of features (ablation)FineRecon · ScanNet testF1: 73.2 -> 75.5Improved
combine TSDF fusion with Gaussian weighting (ablation)FineRecon · ScanNet testF1: 75.5 -> 73.8Hurt
keep image features alongside TSDF depth guidance (ablation)FineRecon · ScanNet testF1: 71.9 -> 75.5Improved
increase output resolution from 4 cm to 0.5 cm (ablation)FineRecon · ScanNet testChamfer distance: 5.15 -> 5.19No clear effect
increase output resolution from 4 cm to 0.5 cm for SimpleReconSimpleRecon · ScanNet testF1: 68.6 -> 66.9Hurt
augment predicted depth maps with random scale in [0.9, 1.1]FineRecon · ScanNet trainingoverfitting to depth guidanceImproved

Later papers that compared with this method

2 later accepted papers report FineRecon as a baseline in their results tables; 2 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 2 of 2 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