AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Pixel Trajectories With Multiscale Contrastive Random Walks

Zhangxing Bian, Allan Jabri, Alexei A. Efros, Andrew Owens

CVPR 2022 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 37 citations (OpenAlex)

Check 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 the regression module to nonparametric multiscale matching (ablation)Multiscale contrastive random walk · KITTI-15 trainall: 9.42 -> 3.86Improved
Add edge-aware smoothness loss (ablation)Full model · KITTI-15 trainall: 3.86 -> 17.43Improved
Add learned feature consistency to the photometric loss (ablation)Full model · KITTI-15 trainall: 5.02 -> 3.86Improved
Keep the regressor constrained near the nonparametric flow estimate (ablation)Full model · KITTI-15 trainall: 10.44 -> 3.86Improved
Add the boundary loss (ablation)Full model · KITTI-15 trainall: 4.88 -> 3.86Improved
Add the contrastive random walk to the regressor-only setup (ablation)PWC-Net flow model · KITTI-15 trainall: 21.45 -> 3.86Improved
Replace Charbonnier photometric loss with learned features (ablation)PWC-Net flow model · KITTI-15 trainall: 5.69 -> 3.86Improved
Combine learned features with Census features (ablation)Photometric loss · KITTI-15 trainall: 3.86 -> 3.10Improved
Use 3-frame training with learned and Census features (ablation)Photometric loss model · KITTI-15 trainall: 3.10 -> 3.03Improved
Increase cycle length from 2 to 4 (ablation)Multiscale contrastive random walk · KITTI-15 trainall: 3.86 -> 3.39Improved
Increase the number of pyramid levels from 1 to 5 (ablation)Multiscale contrastive random walk · KITTI-15 trainall: 8.98 -> 3.86Improved
Increase local attention window from 3 x 3 to 11 x 11 (ablation)Multiscale contrastive random walk · KITTI-15 trainall: 7.21 -> 3.68Improved

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