FlowVVTON: Flow-Guided Mask-Free Video Virtual Try-On

• URL: http://arxiv.org/abs/2608.30450v1
• Date: Mon, 31 Aug 2026 08:37:47 GMT
• Title: FlowVVTON: Flow-Guided Mask-Free Video Virtual Try-On
• Abstract summary: FlowVVTON is a mask-free framework that eliminates parsing mask dependency entirely.<n>A two-stage training strategy establishes mask-free spatial alignment before introducing flow-guided temporal supervision.<n>Experiments on TikTokDress show that FlowVVTON outperforms baselines by substantial margins.
• Score: 13.050523870282374
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Video virtual try-on aims to transfer a target garment onto a moving person across video frames. Current methods rely on human parsing masks or pose keypoints that frequently fail under large motions and occlusions, causing boundary artifacts and temporal inconsistency. A further limitation is that most approaches rely solely on attention mechanisms for temporal modeling, providing no explicit motion supervision. We propose FlowVVTON, a mask-free framework that eliminates parsing mask dependency entirely. Optical flow is used solely as a training-time supervision signal: a flow-warped latent loss, applied across all layers of the generation model, enforces multi-scale temporal consistency by aligning adjacent-frame features under explicit physical motion constraints. A two-stage training strategy establishes mask-free spatial alignment before introducing flow-guided temporal supervision. Experiments on TikTokDress show that FlowVVTON outperforms baselines by substantial margins, particularly in temporal consistency (5.7$\times$ VFID-R improvement over SwiftTry), while requiring no segmentation masks, pose keypoints, or region annotations at any stage.

Related papers

• MASQ: Mask-Aware Spatiotemporal Quantization for Unsupervised Skeleton Action Segmentation [3.245685960209373]
  Untrimmed skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long unsupervised sequences.<n>Recent approaches often rely on discrete quantization to discover action boundaries from motion representations.<n>We propose a novel Mask-aware Action Spatiotemporal Quantization framework.
  arXiv  Detail & Related papers  (2026-08-30T16:40:32Z)
• Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency [74.90075313101933]
  This paper revisits the same optical-flow primitive through a more local supervision design.<n>We use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop.<n>To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism.
  arXiv  Detail & Related papers  (2026-05-07T13:53:31Z)
• RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow [51.43025173196566]
  Monocular scene flow estimation aims to recover dense 3D motion from image sequences.<n>We propose RAFT-MSF++, a self-supervised multi-frame framework that fuses temporal features to jointly estimate depth and scene flow.<n>Experiments show that RAFT-MSF++ achieves 24.14% SF-all on the KITTI Scene Flow benchmark, with a 30.99% improvement over the baseline and better robustness in occluded regions.
  arXiv  Detail & Related papers  (2026-04-21T11:32:49Z)
• Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer [55.9892973179428]
  MoTok is a discrete motion tokenizer that decouples semantic abstraction from fine-grained reconstruction.<n>On HumanML3D, our method significantly improves controllability and fidelity over MaskControl while using only one-sixth of the tokens.
  arXiv  Detail & Related papers  (2026-03-19T17:59:51Z)
• IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation [58.297199313494]
  Implicit methods capture motion semantics directly from driving video, but suffer from identity leakage and entanglement between motion and appearance.<n>We propose a novel implicit motion representation that compresses per-frame motion into compact 1D motion tokens.<n>Our methodology employs a three-stage training strategy to enhance the training efficiency and ensure high fidelity.
  arXiv  Detail & Related papers  (2026-02-07T11:17:20Z)
• Characterizing Motion Encoding in Video Diffusion Timesteps [50.13907856401258]
  We study how motion is encoded in video diffusion timesteps by the trade-off between appearance editing and motion preservation.<n>We identify an early, motion-dominant regime and a later, appearance-dominant regime, yielding an operational motion-appearance boundary in timestep space.
  arXiv  Detail & Related papers  (2025-12-18T21:20:54Z)
• Interactive Video Generation via Domain Adaptation [7.3970992154175494]
  Text-conditioned diffusion models have emerged as powerful tools for high-quality video generation.<n>Recent training-free approaches introduce attention masking to guide trajectory, but this often degrades quality.<n>We identify two key modes failure in these methods, both of which we interpret as domain problems.
  arXiv  Detail & Related papers  (2025-05-30T06:19:47Z)
• PEMF-VTO: Point-Enhanced Video Virtual Try-on via Mask-free Paradigm [21.1235226974745]
  Video Virtual Try-on aims to seamlessly transfer a reference garment onto a target person in a video.<n>Existing methods typically rely on inpainting masks to define the try-on area.<n>We propose PEMF-VTO, a novel Point-Enhanced Mask-Free Video Virtual Try-On framework.
  arXiv  Detail & Related papers  (2024-12-04T04:24:15Z)
• Motion-inductive Self-supervised Object Discovery in Videos [99.35664705038728]
  We propose a model for processing consecutive RGB frames, and infer the optical flow between any pair of frames using a layered representation. We demonstrate superior performance over previous state-of-the-art methods on three public video segmentation datasets.
  arXiv  Detail & Related papers  (2022-10-01T08:38:28Z)
• A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions [17.66624674542256]
  We propose a novel data-driven approach for temporal fusion of scene flow estimates in a multi-frame setup. In a second step, a neural network combines bi-directional scene flow estimates from a common reference frame, yielding a refined estimate. This way, our approach provides a fast multi-frame extension for a variety of scene flow estimators, which outperforms the underlying dual-frame approaches.
  arXiv  Detail & Related papers  (2020-11-03T10:14:11Z)

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.