paper-with-me

홈 › Papers

Spectral Motion Alignment for Video Motion Transfer using Diffusion Models

2024-03-22 · Geon Yeong Park, Hyeonho Jeong, Sang Wan Lee, Jong Chul Ye

The evolution of diffusion models has greatly impacted video generation and understanding. Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the customization of input video with target appearance, motion, etc. Despite these advances, challenges persist in accurately distilling motion information from video frames. While existing works leverage the consecutive frame residual as the target motion vector, they inherently lack global motion context and are vulnerable to frame-wise distortions. To address this, we present Spectral Motion Alignment (SMA), a novel framework that refines and aligns motion vectors using Fourier and wavelet transforms. SMA learns motion patterns by incorporating frequency-domain regularization, facilitating the learning of whole-frame global motion dynamics, and mitigating spatial artifacts. Extensive experiments demonstrate SMA's efficacy in improving motion transfer while maintaining computational efficiency and compatibility across various video customization frameworks.

📄 PDF Abstract BibTeX arXiv:2403.15249

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyVideo Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
SMA Slime Mould Algorithm (SMA) is a new stochastic optimizer proposed based on the oscillation mode of slime mould in nature. SMA has several new features with a unique…

Similar Papers 제목 키워드 기반

MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

2026-04-01 · Samuel Teodoro, Yun Chen, Agus Gunawan, Soo Ye Kim 외 arxiv

Motion transfer enables controllable video generation by transferring temporal dynamics from a reference video to synthesize a new video conditioned on a target caption. However, existing Diffusion Transformer (DiT)-base…

Video Generation

MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation

2025-07-22 · Yanchen Liu, Yanan Sun, Zhening Xing, Junyao Gao 외 arxiv

Existing text-to-video methods struggle to transfer motion smoothly from a reference object to a target object with significant differences in appearance or structure between them. To address this challenge, we introduce…

Text-to-Video Generation

SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer

2024-04-04 · Zijie Wu, Chaohui Yu, Yanqin Jiang, Chenjie Cao 외

Recent advances in 2D/3D generative models enable the generation of dynamic 3D objects from a single-view video. Existing approaches utilize score distillation sampling to form the dynamic scene as dynamic NeRF or dense …

motion predictionNeRF

Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion

2024-08-01 · Manuel Kansy, Jacek Naruniec, Christopher Schroers, Markus Gross 외

Recent years have seen a tremendous improvement in the quality of video generation and editing approaches. While several techniques focus on editing appearance, few address motion. Current approaches using text, trajecto…

Face ReenactmentVideo Generation

REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfer

2022-09-01 · Quanwei Yang, Xinchen Liu, Wu Liu, Hongtao Xie 외

Human Video Motion Transfer (HVMT) aims to, given an image of a source person, generate his/her video that imitates the motion of the driving person. Existing methods for HVMT mainly exploit Generative Adversarial Networ…