AI Paper Atlas

Research map / 3D vision / Human pose estimation

SAC-GNC: SAmple Consensus for adaptive Graduated Non-Convexity

Valter Piedade, Chitturi Sidhartha, José Gaspar, Venu Madhav Govindu, Pedro Miraldo

ICCV 2025 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 0 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 adaptive sigma search (ablation)vanilla GNC · 3DMatch HOME1 low inliers (11.6%)mAA (eR, 5deg): 0.465 -> 0.487Improved
add sigma initialization without sigma search (ablation)vanilla GNC · 3DMatch HOME1 low inliers (11.6%)mAA (eR, 5deg): 0.465 -> 0.457Hurt
add termination criteria and sigma initialization on top of sigma search (ablation)SAC-GNC · 3DMatch HOME1 low inliers (11.6%)Time [ms]: 7.47 -> 5.98Improved
use adaptive annealing instead of fixed gamma 5.0 (ablation)SAC-GNC · 3DMatch HOME1 low inliers (11.6%)mAA (eR, 5deg): 0.446 -> 0.490Improved
use adaptive annealing instead of fixed gamma 1.4 (time) (ablation)SAC-GNC · 3DMatch HOME1 low inliers (11.6%)Time [ms]: 7.45 -> 5.98Improved
more trials and larger queue (SAC-GNC++ vs SAC-GNC) (ablation)SAC-GNC · 3DMatch HOME1 low inliers (11.6%)mAA (eR, 5deg): 0.490 -> 0.505Improved
add SAC-GNC with Geman-McClure loss (ablation)vanilla GNC · 3DMatch HOME1 low inliers (11.6%) robust loss ablationmAA (eR, 5deg): 0.465 -> 0.487Improved
add SAC-GNC with Cauchy loss (ablation)vanilla GNC · 3DMatch HOME1 low inliers (11.6%) robust loss ablationmAA (eR, 5deg): 0.425 -> 0.427No clear effect
add SAC-GNC with Bisquare loss (ablation)vanilla GNC · 3DMatch HOME1 low inliers (11.6%) robust loss ablationmAA (eR, 5deg): 0.147 -> 0.276Improved
add SAC-GNC with Logistic loss (ablation)vanilla GNC · 3DMatch HOME1 low inliers (11.6%) robust loss ablationmAA (eR, 5deg): 0.162 -> 0.157Hurt
use SAC-GNC instead of GNCpGNCp · ModelNet (50.8% inliers)mAA (eR, 5deg): 0.627 -> 0.708Improved
use SAC-GNC instead of RANSACRANSAC · 3DMatch (11.6% inliers)mAA (eR, 5deg): 0.279 -> 0.421Improved

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