Pith. sign in

REVIEW 5 cited by

MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.05275 v1 pith:WTRUD3MW submitted 2024-12-06 cs.CV cs.AI

Tuna Han Salih Meral , Hidir Yesiltepe , Connor Dunlop , Pinar Yanardag This is my paper
classification cs.CVcs.AI
keywords modelsmotionmotionflowvideodiffusioncapabilitiesscenetransfer
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these models generally lack fine-grained control over motion patterns, limiting their practical applicability. We introduce MotionFlow, a novel framework designed for motion transfer in video diffusion models. Our method utilizes cross-attention maps to accurately capture and manipulate spatial and temporal dynamics, enabling seamless motion transfers across various contexts. Our approach does not require training and works on test-time by leveraging the inherent capabilities of pre-trained video diffusion models. In contrast to traditional approaches, which struggle with comprehensive scene changes while maintaining consistent motion, MotionFlow successfully handles such complex transformations through its attention-based mechanism. Our qualitative and quantitative experiments demonstrate that MotionFlow significantly outperforms existing models in both fidelity and versatility even during drastic scene alterations.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    CoMoGen generates controllable interactive video from mask sequences and images by encoding masks into MMDiT via MaskAdapter and LoRA on motion layers, claiming SOTA motion fidelity.

  2. Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    Prompt Relay is an inference-time plug-and-play method that penalizes cross-attention to enforce temporal prompt alignment and reduce semantic entanglement in multi-event video generation.

  3. ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Test-time tuning of video diffusion models collapses generation toward the source video; ElasticTTT counters this with noisy targets, contrastive source-prompt guidance, and asynchronous region-wise noise scheduling, ...

  4. ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A test-time tuning framework with three regularization techniques that preserves the generative prior of a video diffusion model during one-shot editing, achieving state-of-the-art results on the authors' benchmark.

  5. SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation

    cs.CV 2025-06 unverdicted novelty 5.0 of 10

    SynMotion combines disentangled semantic embeddings, parameter-efficient motion adapters, and alternate subject-motion training on a new SPV dataset to improve motion customization in text-to-video and image-to-video ...

Pith tools