AI Paper Atlas

Research map / 3D vision / Face and shape

Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction

Christiane Sommer, Lu Sang, David Schubert, Daniel Cremers

CVPR 2022 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 25 citations (OpenAlex)

Check 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
Store per-voxel SDF gradients and use Taylor expansion rather than trilinear interpolationGradient-SDF depth tracker · TUM RGB-D sequencespose estimation runtime: 100--120 ms -> 30--40 msImproved
Store per-voxel gradients alongside SDF valuesGradient-SDF · Synthetic spheres, voxels within 10v_s of surfacemean angular deviation (degrees): 9.49° -> 5.07°Improved
Use Gradient-SDF hash-map tracking rather than SDF tracking with a hash mapDepth tracking · TUM RGB-Dpose estimation runtime: 100--120 ms -> 30--40 msImproved
Use Gradient-SDF hash-map tracking rather than dense voxel storageDepth-based reconstruction · 00577_sofamemory: more than 20× less memoryImproved
Apply implicit photometric bundle adjustmentGradient-SDF · TUM RGB-D fr1/xyzpose translation RMSE (cm): 2.8 -> 1.0Improved
Apply implicit photometric bundle adjustmentGradient-SDF · TUM RGB-D fr1/teddypose translation RMSE (cm): 6.8 -> 4.4Improved
Apply implicit photometric bundle adjustmentGradient-SDF · TUM RGB-D fr2/xyzpose translation RMSE (cm): 1.8 -> 1.0Improved
Apply implicit photometric bundle adjustmentGradient-SDF · TUM RGB-D fr2/rpypose translation RMSE (cm): 2.7 -> 2.5Improved
Apply implicit photometric bundle adjustmentGradient-SDF · TUM RGB-D fr3/householdpose translation RMSE (cm): 2.1 -> 0.6Improved
Optimize poses only rather than optimizing poses and geometry (ablation)Gradient-SDF bundle adjustment · TUM RGB-D sequencespose translation RMSE (cm): 1.0 -> 1.0; 4.4 -> 4.3; 1.0 -> 1.1; 2.5 -> 2.4; 0.6 -> 0.7No clear effect
Decouple pose optimization across frames (ablation)Gradient-SDF bundle adjustment · TUM RGB-D sequencespose translation RMSE (cm): 1.0 -> 1.2; 4.4 -> 4.6; 1.0 -> 1.0; 2.5 -> 2.5; 0.6 -> 0.6No clear effect
Decouple pose optimization and optimize poses only (ablation)Gradient-SDF bundle adjustment · TUM RGB-D sequencespose translation RMSE (cm): 1.0 -> 1.1; 4.4 -> 4.3; 1.0 -> 1.0; 2.5 -> 2.4; 0.6 -> 0.6No clear effect

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