AI Paper Atlas

Research map / 3D vision / Face and shape

DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

Shih-Yang Su, Timur Bagautdinov, Helge Rhodin

ECCV 2022 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 37 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 learned aggregation network (ablation)DANBO · Human3.6M S9 ablationPSNR: 17.08 -> 24.38Improved
add factorized per-bone volumes (ablation)DANBO · Human3.6M S9 ablationPSNR: 24.24 -> 24.38Improved
add GNN features (ablation)DANBO · Human3.6M S9 ablationPSNR: 23.87 -> 24.38Improved
use Soft-softmax instead of softmax aggregation (ablation)DANBO · Human3.6M S9 ablationPSNR: 23.80 -> 24.38Improved
use Soft-softmax instead of Softmax-OOB (ablation)DANBO · Human3.6M S9 ablationPSNR: 24.00 -> 24.38Improved
use weighted aggregation instead of unweighted Sum-OOB (ablation)DANBO · Human3.6M S9 ablationPSNR: 23.22 -> 24.38Improved
use factorized volume instead of SlabConv full 3D volume (ablation)DANBO · Human3.6M S9 ablationPSNR: 24.17 -> 24.38Improved
DANBO versus A-NeRF in novel view synthesisA-NeRF baseline · Human3.6M novel viewPSNR: 24.21 -> 24.70Improved
DANBO versus A-NeRF in novel pose synthesisA-NeRF baseline · Human3.6M novel posePSNR: 22.96 -> 23.76Improved
DANBO versus A-NeRF on MonoPerfCapA-NeRF baseline · MonoPerfCap novel posePSNR: 23.67 -> 23.25Mixed

Later papers that compared with this method

3 later accepted papers report DANBO as a baseline in their results tables; 3 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