AI Paper Atlas

Research map / 3D vision / Face and shape

Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction

Rohan Chabra, Jan E. Lenssen, Eddy Ilg, Tanner Schmidt, Julian Straub, Steven Lovegrove, Richard Newcombe

ECCV 2020 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 412 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 local latent codes per voxel instead of one global DeepSDF codeDeepLS · 3D Warehouse chairChamfer distance: 0.204 -> 0.030Improved
use local latent codes per voxel instead of one global DeepSDF codeDeepLS · 3D Warehouse lampChamfer distance: 0.832 -> 0.078Improved
use local shapes with a much smaller decoder than DeepSDFDeepLS · Stanford Bunnytraining time to equal accuracy: one minute vs over 8 days of GPU timeImproved
replace TSDF Fusion with DeepLS on synthetic scenesDeepLS · ICL-NUIM meansurface error: 5.42 mm -> 4.92 mmImproved
replace TSDF Fusion with DeepLS on real scansDeepLS · 3D Scene Dataset Burgherssurface error: 10.11 -> 5.74Improved
replace TSDF Fusion with DeepLS on real scansDeepLS · 3D Scene Dataset StoneWallcompletion: 91.02 -> 91.37No clear effect
replace TSDF Fusion with DeepLS under artificial noiseDeepLS · ICL-NUIM with noise sigma 0.015surface error: 7.29 mm -> 6.41 mmImproved
replace TSDF Fusion with DeepLS under artificial noiseDeepLS · ICL-NUIM with noise sigma 0.015completion: 68.53 % -> 71.04 %Improved
increase compression (larger voxels) for DeepLS versus TSDF FusionDeepLS · ICL-NUIM representation size sweepcompleteness: TSDF Fusion drops to about 50% less complete; DeepLS maintains completenessImproved
use trilinear interpolation (partition of unity) between neighboring voxels (ablation)DeepLS · decoder evaluation costdecoder evaluations per query: factor of eightHurt
train codes with extended receptive field (L-infinity radius 1.5 voxel) for border consistency (ablation)DeepLS · voxel boundary SDFaccuracy vs efficiencyImproved
enlarge receptive field of local shapes beyond a critical point (ablation)DeepLS · 2D border consistencySDF prediction errorMixed

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