AI Paper Atlas

Research map / 3D vision / Human pose estimation

Hidden Footprints: Learning Contextual Walkability from 3D Human Trails

Jin Sun, Hadar Averbuch-Elor, Qianqian Wang, Noah Snavely

ECCV 2020 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 4 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 hidden footprint propagation (ablation)MSE-trained model · Waymo 50-scene manually labeled setmAP: 0.111 -> 0.145Improved
add class-balanced (reweighted) BCE instead of standard BCE (ablation)footprint-trained model · Waymo 50-scene manually labeled setmAP: 0.119 -> 0.190Improved
add adversarial feature loss to reweighted BCE (ablation)RBCE model · Waymo 50-scene manually labeled setmAP: 0.190 -> 0.269Improved
add class-balanced loss to adversarial-only training (ablation)adversarial-only model · Waymo 50-scene manually labeled setmAP: 0.173 -> 0.269Improved
add class-balanced + adversarial losses instead of MSE (ablation)MSE model · Waymo 50-scene manually labeled setmAP: 0.145 -> 0.269Improved
add adversarial feature loss to reweighted BCE (ablation)RBCE model · Waymo entire test setPred Valid (TP) ratio: 0.53 -> 0.69Improved
add class-balanced loss to adversarial-only training (ablation)adversarial-only model · Waymo entire test setPred Total (TP+FP) ratio: 22.15 -> 8.18Hurt
use focal loss instead of class-balanced loss (ablation)Ours · Waymo 50-scene manually labeled setperformanceNo clear effect
propagate 3D person labels across the sequenceWaymo labels · Waymo trainlocations per image: 3.8 -> 362Improved
use proposed walkability model instead of semantic-segmentation-based Semantic-NetSemantic-Net · Waymo 50-scene manually labeled setmAP: 0.201 -> 0.269Improved
use proposed model instead of Inpainting baselineInpainting · Waymo 100-scene manually labeled setmAP: 0.107 -> 0.246Improved
use Waymo-trained model on Cityscapes instead of Cityscapes-trained model of Lee et al.Lee et al. · Cityscapes valKL divergence: 0.78 -> 0.42Improved

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