AI Paper Atlas

Research map / 3D vision / Depth and stereo

VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction

Jaesung Choe, Sunghoon Im, Francois Rameau, Minjun Kang, In So Kweon

ICCV 2021 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 72 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 PosedConv instead of standard 3D Conv (ablation)VolumeFusion · ScanNetAbsRel: .058 -> .049Improved
add PosedConv instead of standard 3D Conv (ablation)VolumeFusion · ScanNetF-score: .460 -> .508Improved
use discrete kernel rotation instead of rotation-by-interpolation (ablation)PosedConv · ScanNetRMSE: .223 -> .164Improved
rotate kernels by naive interpolation instead of using standard 3D Conv (ablation)VolumeFusion · ScanNetF-score: .460 -> .487Improved
use two-stage depth fusion instead of single-stage TSDF regression (ablation)Murez et al. single-stage · ScanNetRMSE: .248 -> .164Improved
embed masked depth maps in addition to PosedConv features (ablation)VolumeFusion w/o depth · ScanNetTSDF L1: .159 -> .141Improved
add PosedConv without depth fusion over single-stage (ablation)Murez et al. · ScanNetRMSE: .248 -> .236Improved
add overlapping mask (ablation)VolumeFusion · ScanNetAbsRel: .060 -> .049Improved
add overlapping mask (ablation)VolumeFusion · ScanNetF-score: .475 -> .508Improved
add PosedConv alone without depth fusion or mask (ablation)Single-stage baseline · ScanNetAbsRel: .061 -> .060No clear effect
use VolumeFusion instead of Murez et al.single-stage TSDF regression · ScanNetAbsRel: .061 -> .049Improved
use VolumeFusion instead of Murez et al.single-stage TSDF regression · ScanNetF-score: .499 -> .508Mixed

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