AI Paper Atlas

Research map / 3D vision / Face and shape

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation

Jiteng Mu, Weichao Qiu, Adam Kortylewski, Alan Yuille, Nuno Vasconcelos, Xiaolong Wang

ICCV 2021 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 99 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 test-time adaptation of the shape encoder (ablation)A-SDF · Shape2Motion Oven reconstructionChamfer-L1 (x1000): 3.72 -> 1.83Improved
add test-time adaptation of the shape encoder (ablation)A-SDF · Shape2Motion Fridge reconstructionChamfer-L1 (x1000): 0.90 -> 0.69Improved
add test-time adaptation of the shape encoder (ablation)A-SDF · RBO real depth reconstructionChamfer-L1 (x1000): 2.53 -> 0.76Improved
add test-time adaptation of the shape encoder (ablation)A-SDF · RBO real depth generationChamfer-L1 (x1000): 5.09 -> 3.22Improved
add test-time adaptation of the shape encoder (ablation)A-SDF · Laptop partial point cloud 1-view reconstructionChamfer-L1 (x1000): 2.19 -> 2.25Hurt
add test-time adaptation of the shape encoder (ablation)A-SDF · Laptop partial point cloud 2-view reconstructionChamfer-L1 (x1000): 0.75 -> 0.61Improved
add test-time adaptation of the shape encoder (ablation)A-SDF · Shape2Motion shape synthesis (7 categories)Chamfer-L1 (x1000): 2.86 -> 3.01Mixed
add part label supervision (ablation)A-SDF with TTA · Shape2Motion Washing machine shape synthesisChamfer-L1 (x1000): 3.01 -> 1.96Improved
add part label supervision (ablation)A-SDF with TTA · Shape2Motion Oven shape synthesisChamfer-L1 (x1000): 2.58 -> 3.10Hurt
use disentangled shape and articulation codes instead of single DeepSDF codeA-SDF w/o TTA · Shape2Motion Oven interpolationChamfer-L1 (x1000): 11.13 -> 6.83Improved
use disentangled shape and articulation codes instead of single DeepSDF codeA-SDF w/o TTA · Shape2Motion Laptop interpolationChamfer-L1 (x1000): 2.77 -> 0.17Improved
use disentangled codes instead of single DeepSDF codeA-SDF · Shape2Motion Laptop extrapolationChamfer-L1 (x1000): 3.396 -> 0.280Improved

Later papers that compared with this method

5 later accepted papers report A-SDF as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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