# UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on

arXiv: https://arxiv.org/abs/2608.05745 · HTML: https://mlsanity.com/paper/2608.05745/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 61 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models](https://mlsanity.com/paper/2407.15886/) (2024)
- [Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models](https://mlsanity.com/paper/2601.07372/) (2026)
- [ViViD: Video Virtual Try-on using Diffusion Models](https://mlsanity.com/paper/2405.11794/) (2024)
- [FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on](https://mlsanity.com/paper/2411.10499/) (2024)
- [Qwen-Image-2.0 Technical Report](https://mlsanity.com/paper/2605.10730/) (2026)
- [InstructX: Towards Unified Visual Editing with MLLM Guidance](https://mlsanity.com/paper/2510.08485/) (2025)
- [CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal Concatenation](https://mlsanity.com/paper/2501.11325/) (2025)
- [TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models](https://mlsanity.com/paper/2411.18350/) (2024)
- [DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework](https://mlsanity.com/paper/2508.02807/) (2025)
- [MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on](https://mlsanity.com/paper/2505.21325/) (2025)
- [Dynamic Try-On: Taming Video Virtual Try-on with Dynamic Attention Mechanism](https://mlsanity.com/paper/2412.09822/) (2024)
- [Instruction Tuning for Story Understanding and Generation with Weak Supervision](https://mlsanity.com/paper/2501.15574/) (2025)
- [Video Virtual Try-on with Conditional Diffusion Transformer Inpainter](https://mlsanity.com/paper/2506.21270/) (2025)
- [Once Is Enough: Lightweight DiT-Based Video Virtual Try-On via One-Time Garment Appearance Injection](https://mlsanity.com/paper/2510.07654/) (2025)
- [FW-VTON: Flattening-and-Warping for Person-to-Person Virtual Try-on](https://mlsanity.com/paper/2507.16010/) (2025)

## Built on by (most cited first, 1 of 1)

- [LiveVVT: High-Fidelity Video Virtual Try-On in Real Time](https://mlsanity.com/paper/2608.26714/) (2026)

## Abstract (arXiv)

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.