Search papers, labs, and topics across Lattice.
This paper introduces UniVVT, a unified end-to-end framework for Video Virtual Try-On (VVT) that reframes the task as semantically conditioned video generation, eliminating the need for traditional mask, pose, and warping modules. By employing a scene-task perceiver based on a Multimodal Large Language Model, the framework encodes the source video, target garment, and task instructions into compact latent tokens, allowing for coherent garment transfer without the errors associated with geometric priors. Extensive experiments show that UniVVT achieves state-of-the-art performance across multiple benchmarks, highlighting the effectiveness of implicit semantic guidance over traditional methods.
Implicit semantic guidance in UniVVT outperforms traditional geometric preprocessing, setting a new standard for high-fidelity video virtual try-on.
Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics. Dominant approaches cast VVT as mask-conditioned video inpainting and rely on separate modules for human parsing, pose estimation, and garment warping. This multi-stage design complicates deployment and, more critically, allows errors in explicit geometric priors to propagate irreversibly into the generated video. We present UniVVT, a unified end-to-end framework that reframes VVT as semantically conditioned video generation, eliminating mask, pose, and warping modules at inference. At its core, a scene-task perceiver built on a Multimodal Large Language Model jointly encodes the source video, target garment, and task instruction into compact, task-aware latent tokens, implicitly capturing what to transfer and where and how to transfer it. A lightweight semantic bridge then aligns these tokens with the conditioning space of a diffusion-based video generator, enabling coherent garment transfer. To robustly couple the heterogeneous components, we devise a three-stage progressive training strategy comprising semantic alignment, joint task adaptation, and flexible-resolution refinement. Extensive experiments demonstrate that UniVVT achieves state-of-the-art performance across multiple benchmarks, validating implicit semantic guidance as a simple and effective alternative to fragile geometric preprocessing for end-to-end virtual try-on.
