JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908669987258368 |
|---|---|
| author | Chen, Fangda Zhao, Shanshan Xu, Chuanfu Lan, Long |
| author_facet | Chen, Fangda Zhao, Shanshan Xu, Chuanfu Lan, Long |
| contents | Recent advancements in customized video generation have led to significant improvements in the simultaneous adaptation of appearance and motion. Typically, decoupling the appearance and motion training, prior methods often introduce concept interference, resulting in inaccurate rendering of appearance features or motion patterns. In addition, these methods often suffer from appearance contamination, in which background and foreground elements from reference videos distort the customized video. This paper aims to alleviate these issues by proposing JointTuner. The core motivation of our JointTuner is to enable joint optimization of both appearance and motion components, upon which two key innovations are developed, i.e., Gated Low-Rank Adaptation (GLoRA) and Appearance-independent Temporal Loss (AiT Loss). Specifically, GLoRA uses a context-aware activation layer, analogous to a gating regulator, to dynamically steer LoRA modules toward learning either appearance or motion while maintaining spatio-temporal consistency. Moreover, with the finding that channel-temporal shift noise suppresses appearance-related low-frequencies while enhancing motion-related high-frequencies, we designed the AiT Loss. This loss adds the same shift to the diffusion model's predicted noise during fine-tuning, forcing the model to prioritize learning motion patterns. JointTuner's architecture-agnostic design supports both UNet (e.g., ZeroScope) and Diffusion Transformer (e.g., CogVideoX) backbones, ensuring its customization capabilities scale with the evolution of foundational video models. Furthermore, we present a systematic evaluation framework for appearance-motion combined customization, covering 90 combinations evaluated along four critical dimensions: semantic alignment, motion dynamism, temporal consistency, and perceptual quality. Our project homepage is available online. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23951 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation Chen, Fangda Zhao, Shanshan Xu, Chuanfu Lan, Long Computer Vision and Pattern Recognition Recent advancements in customized video generation have led to significant improvements in the simultaneous adaptation of appearance and motion. Typically, decoupling the appearance and motion training, prior methods often introduce concept interference, resulting in inaccurate rendering of appearance features or motion patterns. In addition, these methods often suffer from appearance contamination, in which background and foreground elements from reference videos distort the customized video. This paper aims to alleviate these issues by proposing JointTuner. The core motivation of our JointTuner is to enable joint optimization of both appearance and motion components, upon which two key innovations are developed, i.e., Gated Low-Rank Adaptation (GLoRA) and Appearance-independent Temporal Loss (AiT Loss). Specifically, GLoRA uses a context-aware activation layer, analogous to a gating regulator, to dynamically steer LoRA modules toward learning either appearance or motion while maintaining spatio-temporal consistency. Moreover, with the finding that channel-temporal shift noise suppresses appearance-related low-frequencies while enhancing motion-related high-frequencies, we designed the AiT Loss. This loss adds the same shift to the diffusion model's predicted noise during fine-tuning, forcing the model to prioritize learning motion patterns. JointTuner's architecture-agnostic design supports both UNet (e.g., ZeroScope) and Diffusion Transformer (e.g., CogVideoX) backbones, ensuring its customization capabilities scale with the evolution of foundational video models. Furthermore, we present a systematic evaluation framework for appearance-motion combined customization, covering 90 combinations evaluated along four critical dimensions: semantic alignment, motion dynamism, temporal consistency, and perceptual quality. Our project homepage is available online. |
| title | JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.23951 |