TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On

• URL: http://arxiv.org/abs/2604.27958v1
• Date: Thu, 30 Apr 2026 14:53:44 GMT
• Title: TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
• Abstract summary: TripVVT is a framework that replaces fragile garment masks with a simple, stable human-mask prior.<n>TripVVT achieves superior video quality and garment fidelity while markedly improving generalization to challenging in-the-wild videos.
• Score: 36.1581419300859
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to the scarcity of large-scale in-the-wild triplet data and the improper use of masks, the performance of video virtual try-on models remains limited. In this paper, we first introduce **TripVVT-10K**, the largest and most diverse in-the-wild triplet dataset to date, providing explicit video-level cross-garment supervision that existing video datasets lack. Built upon this resource, we develop **TripVVT**, a Diffusion Transformer-based framework that replaces fragile garment masks with a simple, stable human-mask prior, enabling reliable background preservation while remaining robust to real-world motion, occlusion, and cluttered scenes. To support comprehensive evaluation, we further establish **TripVVT-Bench**, a 100-case benchmark covering diverse garments, complex environments, and multi-person scenarios, with metrics spanning video quality, try-on fidelity, background consistency, and temporal coherence. Compared to state-of-the-art academic and commercial systems, TripVVT achieves superior video quality and garment fidelity while markedly improving generalization to challenging in-the-wild videos. We publicly release the dataset and benchmark, which we believe provide a solid foundation for advancing controllable, realistic, and temporally stable video virtual try-on.

Related papers

• BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo Data [16.374416879388352]
  Video virtual try on (VVT) aims to generate realistic videos of a person wearing a target garment.<n>Recent methods leverage a-driven video generation paradigm to improve in-the-wild performance, yet they rely on masks to localize try-on regions.<n>We propose Boo-M-VVT, a mask-free VVT framework built upon the paradigm.
  arXiv  Detail & Related papers  (2026-09-03T17:22:33Z)
• UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on [21.69586852578892]
  Video Virtual Try-On (VVT) synthesizes a video of a person wearing a target garment while preserving identity, motion, and scene dynamics.<n>Traditional approaches cast VVT as mask-conditioned video inpainting and rely on separate modules for human parsing, pose estimation, and garment warping.<n>We present UniVVT, a unified end-to-end framework that reframes VVT as semantically conditioned video generation.
  arXiv  Detail & Related papers  (2026-08-06T08:29:47Z)
• InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving [70.7737035270887]
  We introduce InfiniVerse, a unified pipeline for synthesis of dynamic urban scenes from a single frame.<n>InfiniVerse achieves state-of-the-art performance with a FID of 6.4 and FVD of 67.97, significantly outperforming existing benchmarks in both duration and stability.
  arXiv  Detail & Related papers  (2026-06-30T04:08:22Z)
• OmniTryOn: Video Try-On Anything at Once! [32.91851342240063]
  This paper proposes the novel Try-On Anything task, which aims to simultaneously transfer diverse wearable objects onto a person in a video in a single inference pass.<n>We present OmniTryOn, an external-prior-free generative framework designed to tackle this task.<n>Experiments on TryAny-Bench demonstrate that OmniTryOn significantly outperforms existing specialized video virtual try-on models.
  arXiv  Detail & Related papers  (2026-06-07T08:40:43Z)
• SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations [88.8747004592363]
  SceneScribe-1M is a new large-scale, multi-temporal video dataset.<n>It comprises one million in-the-wild videos, each meticulously annotated with detailed textual descriptions, precise parameters, dense depth maps, and consistent 3D point tracks.<n>We demonstrate the versatility and value of SceneScribe-1M by establishing benchmarks across a wide array of downstream tasks, including monocular depth estimation, scene reconstruction dynamic point tracking, as well as generative tasks such as text-to-video synthesis, with or without camera control.
  arXiv  Detail & Related papers  (2026-04-09T08:59:33Z)
• MoCha:End-to-End Video Character Replacement without Structural Guidance [14.573557179926079]
  MoCha is a framework for replacing video characters with a user-provided identity.<n>We introduce a condition-aware RoPE and employ an RL-based post-training stage.<n>We design three specialized datasets: a high-fidelity rendered dataset built with Unreal Engine 5 (UE5), an expression-driven dataset synthesized by current portrait animation techniques, and an augmented dataset derived from existing video-mask pairs.
  arXiv  Detail & Related papers  (2026-01-13T14:10:34Z)
• The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection [90.30501870268911]
  KeyTailor is a novel framework for realistic try-on video.<n>It uses an instruction-guided sampling strategy to filter informative frames from the input video.<n>Our dataset ViT-HD comprises 15, 070 high-quality video samples at a resolution of 810*1080, covering diverse garments.
  arXiv  Detail & Related papers  (2025-12-23T13:15:31Z)
• Generative Video Matting [57.186684844156595]
  Video matting has traditionally been limited by the lack of high-quality ground-truth data.<n>Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations.<n>We introduce a novel video matting approach that can effectively leverage the rich priors from pre-trained video diffusion models.
  arXiv  Detail & Related papers  (2025-08-11T12:18:55Z)
• DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework [26.661935208583756]
  virtual try-on (VVT) technology has garnered considerable academic interest owing to its promising applications in e-commerce advertising and entertainment.<n>We propose DreamVVT, which is inherently capable of leveraging diverse unpaired human-centric data to enhance adaptability in real-world scenarios.<n>In the first stage, we sample representative frames from the input video and utilize a multi-frame try-on model integrated with a vision-language model (VLM), to synthesize high-fidelity and semantically consistent try-on images.<n>In the second stage, skeleton maps together with fine-grained motion and appearance descriptions are
  arXiv  Detail & Related papers  (2025-08-04T18:27:55Z)
• MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on [28.66545985357718]
  Virtual Try-On (VVT) aims to synthesize garments that appear natural across consecutive frames, capturing both their dynamics and interactions with human cues.<n>Existing VVT methods still suffer from inadequate garment fidelity and limitedtemporal consistency.<n>We present MagicTryOn, a diffusion-transformer based framework for garment-constrained video virtual try-on.
  arXiv  Detail & Related papers  (2025-05-27T15:22:02Z)
• WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models [132.77237314239025]
  Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex human movements and occlusions. We reconceptualize video try-on as a process of generating videos conditioned on garment descriptions and human motion. Our solution, WildVidFit, employs image-based controlled diffusion models for a streamlined, one-stage approach.
  arXiv  Detail & Related papers  (2024-07-15T11:21:03Z)
• VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation [79.99551055245071]
  We propose VividPose, an end-to-end pipeline that ensures superior temporal stability. An identity-aware appearance controller integrates additional facial information without compromising other appearance details. A geometry-aware pose controller utilizes both dense rendering maps from SMPL-X and sparse skeleton maps. VividPose exhibits superior generalization capabilities on our proposed in-the-wild dataset.
  arXiv  Detail & Related papers  (2024-05-28T13:18:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.