AI Paper Atlas

Research map / Video / Video generation

Learning to Forecast and Refine Residual Motion for Image-to-Video Generation

Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris Metaxas

ECCV 2018 · Video › Video generation · approach: Trajectory-guided motion control · 99 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 dense connections in the decoder of G_M (ablation)G_M without refinement · MUG facial expression retargetingACD-I: 0.459 -> 0.252Improved
add dense connections in the decoder of G_M (ablation)G_M without refinement · MUG facial expression retargetingACD-C: 0.155 -> 0.140Improved
add dense connections in the decoder of G_M (ablation)G_M without refinement · Penn Action (GT motion maps)MSE: 0.027 -> 0.014Improved
add the refinement network G_R (ablation)G_M with dense connections · MUG facial expression retargetingACD-I: 0.252 -> 0.184Improved
add the refinement network G_R (ablation)G_M with dense connections · MUG facial expression retargetingACD-C: 0.140 -> 0.107Improved
add the refinement network G_R (ablation)G_M with dense connections · Penn Action (GT motion maps)MSE: 0.014 -> 0.011Improved
use residual motion/content mask formulation instead of plain difference map (Villegas et al.) (ablation)motion forecasting network · Penn ActionMSE: 0.030 -> 0.023Improved
use residual motion/content mask formulation instead of plain difference map (Villegas et al.), GT motion maps (ablation)motion forecasting network · Penn Action (GT motion maps)MSE: 0.025 -> 0.011Improved
use 3DMM-based condition with temporal refinement versus MoCoGANvideo generator · MUG facial expression retargetingACD-I: 0.291 -> 0.184Improved

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