AI Paper Atlas

Research map / Video / Video generation

Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization

Liao Shen, Wentao Jiang, Yiran Zhu, Jiahe Li, Tiezheng Ge, Zhiguo Cao, Bo Zheng

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 7 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 IPRO facial reward fine-tuningWan2.2 A14B · Small-face eval (600 scenes)FaceSim: 0.5780 -> 0.6942Improved
Add IPRO facial reward fine-tuningIn-house I2V 15B · Small-face eval (600 scenes)FaceSim: 0.4769 -> 0.6960Improved
Add IPRO facial reward fine-tuningWan2.2 5B · Small-face eval (600 scenes)FaceSim: 0.3788 -> 0.5460Improved
Add IPRO facial reward fine-tuningWan2.2 A14B · VBench-I2VDynamic Degree: 19.45 -> 19.17Mixed
Use facial reward instead of DPOWan2.2 A14B · Small-face eval (600 scenes)FaceSim: 0.6284 -> 0.6942Improved
Use facial reward instead of GRPOWan2.2 A14B · Small-face eval (600 scenes)FaceSim: 0.6334 -> 0.6942Improved
Use reward feedback instead of SFT with auxiliary face loss (ablation)Wan2.2 A14B · Small-face eval (600 scenes)FaceSim: 0.6392 -> 0.6942Improved
Use ArcFace instead of CLIP as reward encoder (ablation)Wan2.2 A14B · Small-face eval (600 scenes)FaceSim: 0.6099 -> 0.6942Improved
Backprop through final low-noise steps instead of high-noise steps (ablation)Wan2.2 A14B · Small-face eval (600 scenes)FaceSim: 0.6456 -> 0.6942Improved
Add KL regularization (ablation)IPRO · Small-face eval (600 scenes)Reward hacking rate: 58% -> 10%Improved
Add facial scoring mechanism (FSM) (ablation)IPRO · Small-face eval (600 scenes)Reward hacking rate: 52% -> 10%Improved
Add KL regularization and FSM (ablation)IPRO · Small-face eval (600 scenes)FaceSim: 0.7544 -> 0.6942 (KL), 0.7388 -> 0.6942 (FSM)Hurt

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