Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction
Dong Li, Wenqi Zhong, Wei Yu, Yingwei Pan, Dingwen Zhang, Ting Yao, Junwei Han, Tao Mei
摘要
Video virtual try-on aims to seamlessly dress a subject in a video with a specific garment. The primary challenge involves preserving the visual authenticity of the garment while dynamically adapting to the pose and physique of the subject. While existing methods have predominantly focused on image-based virtual try-on, extending these techniques directly to videos often results in temporal inconsistencies. Most current video virtual try-on approaches alleviate this challenge by incorporating temporal modules, yet still overlook the critical spatiotemporal pose interactions between human and garment. Effective pose interactions in videos should not only consider spatial alignment between human and garment poses in each frame but also account for the temporal dynamics of human poses throughout the entire video. With such motivation, we propose a new framework, namely Dynamic Pose Interaction Diffusion Models (DPIDM), to leverage diffusion models to delve into dynamic pose interactions for video virtual try-on. Technically, DPIDM introduces a skeleton-based pose adapter to integrate synchronized human and garment poses into the denoising network. A hierarchical attention module is then exquisitely designed to model intraframe human-garment pose interactions and long-term human pose dynamics across frames through pose-aware spatial and temporal attention mechanisms. Moreover, DPIDM capitalizes on a temporal regularized attention loss between consecutive frames to enhance temporal consistency. Extensive experiments conducted on VITON-HD, VVT and ViViD datasets demonstrate the superiority of our DPIDM against the baseline methods. Notably, DPIDM achieves VFID score of 0.506 on VVT dataset, leading to 60.5% improvement over the state-of-the-art GPD-VVTO approach. * Equal contribution. This work was performed at HiDream.ai. Figure 1. Given a garment and a person video, DPIDM generates a lifelike video that preserves the visual authenticity of the garment while adapting to the individual's pose and physique.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic GuidanceJun Zheng, Zhengze Xu, Mengting Chen, Chen Wenyin 等ICML 2026 · 被引用 1 次
- FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image InpaintingChao Gong, Dong Li, Yingwei Pan, Jingjing Chen 等AAAI 2026
- In-Context Generation with Regional Constraints for Instructional Video EditingZhongwei Zhang, Fuchen Long, Wei Li, Zhaofan Qiu 等ICML 2026
它引用的顶会 Paper29
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- TSM: Temporal Shift Module for Efficient Video UnderstandingJi Lin, Chuang Gan, Song HanICCV 2019 · 被引用 2,049 次
相关 Paper
- GPD-VVTO: Preserving Garment Details in Video Virtual Try-OnYuanbin Wang, Weilun Dai, Long Chan, Huanyu Zhou 等ACM MM 2024 · 被引用 4 次
- 3DV-TON: Textured 3D-Guided Consistent Video Try-on via Diffusion ModelsMin Wei, Chaohui Yu, Jingkai Zhou, Fan WangACM MM 2025 · 被引用 1 次
- Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in VideosZhengze Xu, Mengting Chen, Zhao Wang, Linyu Xing 等ACM MM 2024 · 被引用 14 次
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-OnXu Yang, Changxing Ding, Zhibin Hong, Junhao Huang 等CVPR 2024 · 被引用 25 次
- SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion ModelsHung Nguyen, Quang Qui-Vinh Nguyen, Khoi Nguyen, Rang NguyenAAAI 2025 · 被引用 13 次
