AI Paper Atlas

Research map / Video / Video segmentation and tracking

Disentangling Propagation and Generation for Video Prediction

Hang Gao, Huazhe Xu, Qi-Zhi Cai, Ruth Wang, Fisher Yu, Trevor Darrell

ICCV 2019 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 104 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 computed sparse occlusion map and inpainting over warp-only (ablation)DPG · KITTI FlowPSNR: 21.6 -> 22.3Improved
add computed sparse occlusion map and inpainting over warp-only (ablation)DPG · KITTI FlowLPIPS: 0.139 -> 0.114Improved
add occlusion map guidance to an auto-encoder refinement (ablation)DPG · KITTI FlowPSNR: 21.3 -> 22.3Improved
add occlusion map guidance to an auto-encoder refinement (ablation)DPG · KITTI FlowLPIPS: 0.120 -> 0.114Improved
use computed occlusion map instead of learned occlusion map (ablation)DPG · KITTI FlowPSNR: 21.8 -> 22.3Improved
use computed occlusion map instead of learned occlusion map (ablation)DPG · KITTI FlowLPIPS: 0.179 -> 0.114Improved
use computed occlusion map instead of learned map for localizing occlusions (ablation)occlusion map · RoamingImagesIoU: 0.0411 -> 24.91Improved
use masking weight beta=10 instead of beta=1 (ablation)DPG · KITTI FlowPSNR: 21.2 -> 22.3Improved
use masking weight beta=10 instead of beta=0 (unmasked only) (ablation)DPG · KITTI FlowPSNR: 20.7 -> 22.3Improved
use beta=10 instead of beta=infinity (masked pixels only) (ablation)DPG · KITTI FlowPSNR: 18.4 -> 22.3Improved
disentangled flow plus inpainting over pixel-based DVF warping modelDPG vs DVF · KITTI FlowLPIPS: 16.3 -> 11.4Improved
disentangled DPG versus ContextVP on CalTechDPG vs ContextVP · CalTech PedestrianPSNR: 28.7 -> 28.2Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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