AI Paper Atlas

Research map / 3D vision / Face and shape

SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images

Chen-Hsuan Lin, Chaoyang Wang, Simon Lucey

NeurIPS 2020 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 14 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
Use SDF-SRN instead of SoftRasShapeNet airplane reconstruction with unassociated views · ShapeNet airplaneaccuracy (×10; lower is better): 0.250 -> 0.193Improved
Use SDF-SRN instead of SoftRasShapeNet car reconstruction with unassociated views · ShapeNet caraccuracy (×10; lower is better): 0.356 -> 0.141Improved
Use SDF-SRN instead of SoftRasShapeNet chair reconstruction with unassociated views · ShapeNet chairaccuracy (×10; lower is better): 0.690 -> 0.352Improved
Use SDF-SRN instead of CMRPASCAL3D+ airplane reconstruction · PASCAL3D+ airplaneaccuracy (×10; lower is better): 0.625 -> 0.582Improved
Use SDF-SRN instead of CMRPASCAL3D+ car reconstruction · PASCAL3D+ caraccuracy (×10; lower is better): 0.474 -> 0.391Improved
Use SDF-SRN instead of CMRPASCAL3D+ chair reconstruction · PASCAL3D+ chairaccuracy (×10; lower is better): 1.396 -> 0.478Improved
Use an SDF objective rather than binary occupancy classification (ablation)SDF-SRN · ShapeNet chairsaccuracy (×10; lower is better): 0.425 -> 0.352Improved
Add rendering loss (L_RGB) (ablation)SDF-SRN · ShapeNet chairscoverage (×10; lower is better): 0.554 -> 0.315Improved
Add importance weighting (ablation)SDF-SRN · ShapeNet chairscoverage (×10; lower is better): 1.168 -> 0.315Improved
Add positional encoding (ablation)SDF-SRN · ShapeNet chairsaccuracy (×10; lower is better): 0.444 -> 0.352Improved
Optimize the latent code at test time with known camera pose (ablation)SDF-SRN · ShapeNet chairsaccuracy (×10; lower is better): 0.352 -> 0.332Improved

Later papers that compared with this method

3 later accepted papers report SDF-SRN as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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