AI Paper Atlas

Research map / 3D vision / Human pose estimation

Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondences

Shishir Reddy Vutukur, Junwen Huang, Rasmus Laurvig Haugaard, Benjamin Busam, Tolga Birdal

ECCV 2024 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 2 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 CAD-model supervision (Alignist) when training on only 10k imagesAlignist on SYMSOL-I · SYMSOL-Ilog-likelihood: 10.64 -> 9.69 (only 0.95 drop with 10k images vs NF 5.06)Improved
use cube-vertex positional encoding instead of IPDF PE (ablation)Alignist · SYMSOL-Ilog-likelihood: 10.09 -> 10.2 (IPDF PE vs cube PE, grid-5)Improved
use Wigner matrix encoding instead of IPDF PE (ablation)Alignist · SYMSOL-Ilog-likelihood: 10.09 -> 8.59Hurt
mode-focused grid sampling instead of random sampling (ablation)Alignist cube PE · SYMSOL-Ilog-likelihood: 6.94 -> 10.2 (random vs grid-5)Improved
increase sampling grid resolution from grid-5 to grid-6 (ablation)Alignist · SYMSOL-Ilog-likelihood: 10.2 -> 10.48 (L1 loss)Improved
combine SDF shape expert and SurfEmb feature expert (ablation)Alignist · SYMSOL-Ilog-likelihood: 10.32 (S) / 10.18 (F) -> 10.648 (F+S)Improved
replace L1 loss with generalized KL divergence (ablation)Alignist · SYMSOL-Ilog-likelihood: 10.48 -> 10.648Improved
replace L1 loss with GKL (ablation)Alignist · T-Lesslog-likelihood: 13.8 -> 14.53Improved
train SurfEmb on PBR plus real data instead of PBR only (ablation)Alignist · T-Lesslog-likelihood: 13.6 -> 13.8Improved
rely on SurfEmb expert only because SDF expert is uniform on the Sphere objectAlignist · SYMSOL-II (SphereX)log-likelihood: 10.93 vs NF 12.37Hurt
use Alignist with CAD prior versus NF at full dataAlignist vs Normalizing Flow · SYMSOL-IIlog-likelihood: 11.83 vs 12.94Hurt
longer training of Normalizing Flow (100k to 900k iterations)Normalizing Flow · SYMSOL-Ilog-likelihood: avg 5.06 -> 5.82 (10k images); icosa -2.14 -> -6.03Mixed

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