Cover Image

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xue, Haotian, Chen, Qi, Wang, Zhonghao, Huang, Xun, Shechtman, Eli, Xie, Jinrong, Chen, Yongxin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MotionStream: Real-Time Video Generation with Interactive Motion Controls
by: Shin, Joonghyuk, et al.
Published: (2025)

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
by: Huang, Xun, et al.
Published: (2025)

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
by: Xue, Haotian, et al.
Published: (2024)

Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
by: Chen, Yipu, et al.
Published: (2024)

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
by: Xue, Haotian, et al.
Published: (2023)

Causality in Video Diffusers is Separable from Denoising
by: Bai, Xingjian, et al.
Published: (2026)

Diffusion Adversarial Post-Training for One-Step Video Generation
by: Lin, Shanchuan, et al.
Published: (2025)

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance
by: Li, Quanhao, et al.
Published: (2026)

Generative Video Motion Editing with 3D Point Tracks
by: Lee, Yao-Chih, et al.
Published: (2025)

Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video
by: Li, Xiao, et al.
Published: (2025)

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
by: Yin, Tianwei, et al.
Published: (2024)

MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training
by: Uchida, Kengo, et al.
Published: (2024)

VideoGigaGAN: Towards Detail-rich Video Super-Resolution
by: Xu, Yiran, et al.
Published: (2024)

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
by: Wang, Jianyi, et al.
Published: (2025)

MoCrop: Training Free Motion Guided Cropping for Efficient Video Action Recognition
by: Huang, Binhua, et al.
Published: (2025)

MoVideo: Motion-Aware Video Generation with Diffusion Models
by: Liang, Jingyun, et al.
Published: (2023)

MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion
by: Tu, Shuyuan, et al.
Published: (2024)

Long-Context State-Space Video World Models
by: Po, Ryan, et al.
Published: (2025)

FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
by: Wang, Zhen, et al.
Published: (2026)

Stochastic Motion Planning as Gaussian Variational Inference: Theory and Algorithms
by: Yu, Hongzhe, et al.
Published: (2023)

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
by: Fan, Jiaojiao, et al.
Published: (2024)

MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion
by: Susladkar, Onkar, et al.
Published: (2024)

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
by: Shi, Qingyu, et al.
Published: (2025)

MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer
by: Liu, Penghui, et al.
Published: (2025)

No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts
by: Macaluso, Girolamo, et al.
Published: (2025)

One-Step Diffusion Model for Image Motion-Deblurring
by: Liu, Xiaoyang, et al.
Published: (2025)

Moaw: Unleashing Motion Awareness for Video Diffusion Models
by: Zhang, Tianqi, et al.
Published: (2026)

MotionClone: Training-Free Motion Cloning for Controllable Video Generation
by: Ling, Pengyang, et al.
Published: (2024)

MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
by: Bhowmik, Aritra, et al.
Published: (2025)

Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps
by: Maldonado, Gabriel, et al.
Published: (2025)

MotionMatcher: Motion Customization of Text-to-Video Diffusion Models via Motion Feature Matching
by: Wu, Yen-Siang, et al.
Published: (2025)

MotionMaster: Training-free Camera Motion Transfer For Video Generation
by: Hu, Teng, et al.
Published: (2024)

RoMo: Robust Motion Segmentation Improves Structure from Motion
by: Goli, Lily, et al.
Published: (2024)

Video Diffusion Models are Training-free Motion Interpreter and Controller
by: Xiao, Zeqi, et al.
Published: (2024)

ViMo: Generating Motions from Casual Videos
by: Qiu, Liangdong, et al.
Published: (2024)

Encoder-Quantization-Motion-based Video Quality Metrics
by: Chen, Yixu, et al.
Published: (2024)

MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
by: Shi, Shuwei, et al.
Published: (2024)

MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models
by: Li, Xiaomin, et al.
Published: (2024)

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
by: Huang, Hsiang-Wei, et al.
Published: (2026)

Improved Baselines with Representation Autoencoders
by: Singh, Jaskirat, et al.
Published: (2026)