AI Paper Atlas

Research map / Video / Video generation

MIMIC: Mask-Injected Manipulation Video Generation with Interaction Control

Tianxiao Chen, Jintao Rong, Huajin Chen, Jingya Wang, Tao Zhou, Jiming Chen, Qi Ye

ICLR 2026 · Video › Video generation · approach: Trajectory-guided motion control

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 Pair Prompt Control in Stage II (ablation)MIMIC · Manipulation video generation (reference-based)Interaction Rationality (MLLM): 3.8789 -> 4.1381Improved
add Pair Prompt Control in Stage II (ablation)MIMIC · Manipulation video generation (reference-based)Semantic Similarity (MLLM): 2.7526 -> 2.9127Improved
add IMA attention module in Stage I (ablation)MIMIC · Manipulation video generation (reference-based)Interaction Rationality (MLLM): 3.6216 -> 4.1381Improved
add IMA attention module in Stage I (ablation)MIMIC · Manipulation video generation (reference-based)Text Alignment: 0.2548 -> 0.2721Improved
use two-stage (mask then video) instead of one-stage generation (ablation)MIMIC · Manipulation video generation (reference-based)Appearance Consistency: 0.8709 -> 0.9084Improved
use full image rather than masks only as Stage I condition (ablation)MIMIC · Manipulation video generation (reference-based)Interaction Rationality (MLLM): 3.5689 -> 4.1381Improved
use full image rather than masks only as Stage I condition (ablation)MIMIC · Manipulation video generation (reference-based)Subject Consistency: 0.8745 -> 0.9291Improved
add Adaptive Region Loss (lambda 1.00) over original diffusion loss (ablation)MIMIC Stage II · SSv2 10k subset, hand interaction (Adaptive Region Loss)Appearance Consistency: 0.8927 -> 0.9054Improved
add first-frame mask to Adaptive Region Loss (ablation)MIMIC Stage II · SSv2 10k subset, hand interaction (Adaptive Region Loss)Appearance Consistency: 0.9042 -> 0.9054No clear effect
set Adaptive Region Loss weight lambda to 0.50 (ablation)MIMIC Stage II · SSv2 10k subset, hand interaction (Adaptive Region Loss)Subject Consistency: 0.8894 -> 0.8709Hurt
MIMIC vs strongest baseline FlexiAct on MLLM interaction rationalityMIMIC · Manipulation video generation (reference-based)Interaction Rationality (MLLM): 3.5529 -> 4.1381Improved
MIMIC vs MotionClone on text alignmentMIMIC · Manipulation video generation (reference-based)Text Alignment: 0.2947 -> 0.2721Hurt

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