AI Paper Atlas

Research map / Video / Video generation

ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning

Jian Shi, Zhenyu Li, Peter Wonka

ICML 2026 · Video › Video generation · approach: Trajectory-guided motion control · 0 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 implicit disparity guidance (ablation)ImmersePro · YouTube-SBSconvergenceImproved
add layered disparity (ablation)ImmersePro · YouTube-SBSL1: 0.0885 -> 0.0570Improved
add spatial-temporal attention blocks (ablation)ImmersePro · YouTube-SBSL1: 0.0593 -> 0.0570Improved
add context fusion module (ablation)ImmersePro · YouTube-SBSMEt3R: 5.34 -> 5.29Improved
swap DepthAnything for MiDaS in disparity branch (ablation)ImmersePro w/o context fusion · YouTube-SBSL1: 0.0588 -> 0.0590No clear effect
add flow-guided feature propagation (ablation)ImmersePro · YouTube-SBSdisparity learningHurt
use signed mask selection Algorithm 2 instead of Algorithm 1 (ablation)layered disparity · YouTube-SBSimplicit disparity qualityHurt
replace explicit disparity maps with implicit disparity guidance, vs Stereo-from-monoImmersePro · YouTube-SBSPSNR: 20.77 -> 21.83Improved

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