AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

MetaSDF: Meta-Learning Signed Distance Functions

Vincent Sitzmann, Eric Chan, Richard Tucker, Noah Snavely, Gordon Wetzstein

NeurIPS 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 112 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 gradient-based meta-learning instead of auto-decoder latent optimizationshape-space learning · ShapeNet planes dense SDFmean Chamfer distance: 0.073 -> 0.053Improved
use gradient-based meta-learning instead of auto-decoder latent optimizationshape-space learning · ShapeNet tables dense SDFmean Chamfer distance: 0.553 -> 0.134Improved
use gradient-based meta-learning instead of auto-decoder latent optimizationshape-space learning · ShapeNet 3D reconstructioninference time: 8 seconds to 0.4 secondsImproved
use gradient-based meta-learning instead of PointNet set encoderconditioning on zero-level set points · ShapeNet planesmean Chamfer distance: 0.558 -> 0.139Improved
use gradient-based meta-learning instead of PointNet set encoderconditioning on zero-level set points · ShapeNet tablesmean Chamfer distance: 0.693 -> 0.327Improved
use gradient-based meta-learning instead of latent-code optimization2D SDF inference · MNIST SDFsinference time: 4 seconds -> 50 msImproved
replace clamped l1 loss with composite SDF + sign loss (ablation)DeepSDF · ShapeNet planesChamfer distanceNo clear effect
use composite SDF + sign loss instead of clamped l1 in inner loop (ablation)MetaSDF · ShapeNettraining stabilityImproved

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