AI Paper Atlas

Research map / 3D vision / Depth and stereo

CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matching

Samia Shafique, Shu Kong, Charless Fowlkes

ECCV 2024 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 6 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 crime-scene data augmentation (occlusion, erasure, noise) to training (ablation)CriSp · val-FIDmAP@100: 0.0174 -> 0.2071Improved
add data augmentation to ZSE-SBIR (ablation)ZSE-SBIR · val-FIDhit@100: 0.0943 -> 0.4528Improved
match against tread depth maps only instead of RGB, print or all three (ablation)database image configuration · FID-cleanmAP@100: 0.066 (RGB) -> 0.203 (depth)Improved
combine RGB, depth and print in database images (ablation)database image configuration · FID-cleanmAP@100: 0.203 -> 0.057Hurt
add occlusion, erasure and noise augmentations together (ablation)ResNet50 with SupCon · FID-crimehit@100: 0.009 -> 0.226Improved
add occlusion augmentation alone (ablation)ResNet50 with SupCon · FID-crimehit@100: 0.009 -> 0.019No clear effect
use spatial features by removing last pooling (ablation)ResNet50 · val-FID FID-crimehit@100: 0.2264 -> 0.3585Improved
add spatial feature masking (ablation)ResNet50 · val-FID FID-crimehit@100: 0.3585 -> 0.4245Improved
add query print masking during training (ablation)CriSp Enc · val-FID FID-crimehit@100: 0.4528 -> 0.5472Improved
train prior methods with simulated partial-print masksFIRe, SupCon, ZSE-SBIR · val-FIDmAP@100: FIRe 0.0398 -> 0.0030; SupCon 0.0096 -> 0.0001Hurt
match MCNCC against clean shoeprints instead of tread depth mapsMCNCC · val-FIDhit@100: 0.0849 -> 0.0283Hurt

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