AI Paper Atlas

Research map / 3D vision / Depth and stereo

Outdoor inverse rendering from a single image using multiview self-supervision

Ye Yu, William A. P. Smith

TPAMI 2021 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 21 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 VGG perceptual loss (ablation)InverseRenderNet-style full model · Illumination estimation (global scale)lighting MSE: 0.053 -> 0.038Improved
add VGG perceptual loss (ablation)full model · MegaDepth reflectanceMSE: 0.0095 -> 0.0093Improved
add VGG perceptual loss (ablation)full model · IIWWHDR: 21.6 -> 21.1Improved
add cross-projection (albedo consistency) loss (ablation)full model · MegaDepth reflectanceMSE: 0.0153 -> 0.0093Improved
add cross-projection loss (ablation)full model · Illumination estimation (global scale)lighting MSE: 0.052 -> 0.038Improved
add cross-rendering loss (ablation)full model · MegaDepth reflectanceMSE: 0.0101 -> 0.0093Improved
add cross-rendering loss (ablation)full model · IIWWHDR: 21.4 -> 21.1Improved
add cross-rendering loss (ablation)full model · Illumination estimation (global scale)lighting MSE: 0.052 -> 0.038Improved
add cross-projection loss (ablation)full model · IIWWHDR: 21.6 -> 21.1Improved
self-supervised MVS training vs supervised MegaDepth normalsours vs MegaDepth · MegaDepth testnormal mean angular error: 43.6 -> 31.2Improved
self-supervised multiview training vs InverseRenderNetours · MegaDepth testnormal mean angular error: 40.0 -> 31.2Improved
tune loss weights w1,w3,w4 per task instead of uniform weights (ablation)full model · evaluation metricsmixedMixed

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