AI Paper Atlas

Research map / 3D vision / Human pose estimation

DECO: Dense Estimation of 3D Human-Scene Contact In The Wild

Shashank Tripathi, Agniv Chatterjee, Jean-Claude Passy, Hongwei Yi, Dimitrios Tzionas, Michael J. Black

ICCV 2023 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 36 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 DECO scene+part cross-attention architecture instead of BSTRO3D contact estimation · RICH test (RICH-only training)F1: 0.63 -> 0.70Improved
add 2D pixel anchoring loss (ablation)DECO · RICH testgeodesic error (cm): 17.92 -> 10.46 (F1 0.70 -> 0.69)Improved
add scene and part segmentation branch losses (ablation)DECO · RICH testgeodesic error (cm): 23.54 -> 17.92Improved
use separate encoders instead of a shared encoder without branch losses (ablation)DECO · RICH testgeodesic error (cm): 20.85 -> 23.54Hurt
use HRNet backbone instead of Swin (ablation)DECO · RICH testF1: 0.66 -> 0.70Improved
train on additional PROX and DAMON dataDECO vs BSTRO · DAMON testF1: 0.46 -> 0.55 (BSTRO vs DECO)Improved
predict contact directly instead of computing geometric contact from reconstructed humans and objectscontact estimation · DAMON subsetsF1: 0.08 -> 0.48 (CHORE vs DECO)Improved
use DECO-inferred contact in PROX body fitting instead of no contactHPS optimization · PROX quantitativeV2V error: 183.3 -> 171.6Improved
relax GMoF robust scale rho_C from 5e-02 to 1.0 with DECO contacts (ablation)HPS optimization · PROX quantitativeV2V error: 171.6 -> 169.0Improved
increase GMoF robust scale rho_C beyond 1.0 (to 5.0) (ablation)HPS optimization · PROX quantitativeV2V error: 169.0 -> 183.5Hurt

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