AI Paper Atlas

Research map / Video / Video segmentation and tracking

Exploiting Temporal Consistency for Real-Time Video Depth Estimation

Haokui Zhang, Chunhua Shen, Ying Li, Yuanzhouhan Cao, Yu Liu, Youliang Yan

ICCV 2019 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 144 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 CLSTM temporal modelling with 3 input frames instead of a 2D CNN (ablation)2DCNN · NYU Depth V2Rel: 0.139 -> 0.134Improved
increase input frames from 3 to 5 (ablation)ST-CLSTM · NYU Depth V2Rel: 0.134 -> 0.132Improved
increase input frames from 3 to 5 (ablation)ST-CLSTM · NYU Depth V2delta1: 0.824 -> 0.833Improved
replace the 3-layer conv 2DCNN with ST-CLSTM (5 frames) (ablation)2DCNN · NYU Depth V2RMS: 0.585 -> 0.572Improved
replace the 2DCNN with ST-CLSTM (5 frames) (ablation)2DCNN · KITTIRel: 0.111 -> 0.104Improved
replace the 2DCNN with ST-CLSTM (5 frames) (ablation)2DCNN · KITTIRMS: 4.385 -> 4.139Improved
add 3D CNN generative adversarial temporal loss (ablation)ST-CLSTM · NYU Depth V2Rel: 0.132 -> 0.131No clear effect
add 3D CNN generative adversarial temporal loss (ablation)ST-CLSTM · KITTIRel: 0.104 -> 0.101Improved
add 3D CNN generative adversarial temporal loss (ablation)ST-CLSTM · KITTIdelta1: 0.883 -> 0.890Improved
add ST-CLSTM temporal modelling (ablation)2DCNN baseline · NYU Depth V2TCC: 0.846 -> 0.866Improved
add 3D CNN discriminator temporal loss (ablation)ST-CLSTM · NYU Depth V2TCC: 0.866 -> 0.870Improved
add 3D CNN discriminator temporal loss (ablation)ST-CLSTM · NYU Depth V2TMC: 0.962 -> 0.965Improved

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