AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data

Eldar Insafutdinov, Dylan Campbell, João F. Henriques, Andrea Vedaldi

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 12 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 learned symmetry (SNeS) to NeuSNeuS · CO3D cars, random splitMAE depth: 0.108 -> 0.086Improved
add learned symmetry (SNeS) to NeuSNeuS · CO3D cars, random splitIoU mask: 0.523 -> 0.787Improved
add learned symmetry (SNeS) to NeuSNeuS · CO3D cars, random splitPSNR: 23.3 -> 23.3No clear effect
add learned symmetry (SNeS) to NeuSNeuS · CO3D cars, structured splitMAE depth: 0.105 -> 0.077Improved
add learned symmetry (SNeS) to NeuSNeuS · CO3D cars, structured splitIoU mask: 0.566 -> 0.906Improved
add learned symmetry (SNeS) to NeuSNeuS · CO3D cars, structured splitPSNR: 13.4 -> 14.1Improved
add learned symmetry (SNeS) to NeuSNeuS · CO3D cars, structured splitLPIPS: 0.556 -> 0.503Improved
add symmetric lighting loss (ablation)SNeS · CO3D cars, structured split subsetPSNR: 14.3 -> 13.7Hurt
add symmetric lighting loss (ablation)SNeS · CO3D cars, structured split subsetLPIPS: 0.564 -> 0.585Hurt
add symmetric lighting loss (ablation)SNeS · CO3D cars, structured split subsetIoU mask: 0.894 -> 0.914Improved
add diffuse colour loss (ablation)SNeS · CO3D cars, structured split subsetMAE depth: 0.0722 -> 0.0706Improved
add diffuse colour loss (ablation)SNeS · CO3D cars, structured split subsetIoU mask: 0.917 -> 0.894Hurt

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