AI Paper Atlas

Research map / Video / Video generation

SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation

Xuancheng Xu, Yaning Li, Sisi You, Bing-Kun Bao

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 5 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 subject representation alignment (DINOv2 target) (ablation)SMRABooth · Customized video generationDINO-I: 0.467 -> 0.519Improved
add subject representation alignment (ablation)SMRABooth · Customized video generationCLIP-I: 0.667 -> 0.700Improved
add motion representation alignment (optical flow) (ablation)SMRABooth · Customized video generationMotion Fidelity: 60.02 -> 62.89Improved
add motion representation alignment (ablation)SMRABooth · Customized video generationImaging Quality: 61.29 -> 67.46Improved
use sparse LoRA layers instead of full layers for both LoRAs (ablation)SMRABooth · Customized video generationCLIP-I: 0.652 -> 0.700Improved
add FFN.0 to subject LoRA (ablation)SMRABooth · Customized video generationDINO-I: 0.357 -> 0.519Improved
add FFN.0 to motion LoRA (ablation)SMRABooth · Customized video generationMotion Fidelity: 56.12 -> 62.89Improved
use time-split subject LoRA weights (low before Tpoint=15, doubled after) (ablation)SMRABooth · Customized video generationvideo qualityImproved
compare SMRABooth to DualReal on WAN2.1WAN2.1 customization · Customized video generationMotion Fidelity: 45.75 -> 62.89Improved
add LoRAs only (baseline) vs plain WAN2.1WAN2.1 · Customized video generationSubject Consistency / Imaging Quality: DINO-I 0.165 -> 0.464; Imaging Quality 65.12 -> 55.90Mixed
add full SMRABooth vs ablated variants on subject consistency (ablation)SMRABooth · Customized video generationSubject Consistency: 95.31 vs 95.29 (w/o SuRA)No clear effect

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