Pith. sign in

REVIEW 12 cited by

FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.10499 v2 pith:ZOJGTCLD submitted 2024-11-15 cs.CV

FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on

classification cs.CV
keywords garmentdetailstry-onfitditfittinggarmentshigh-fidelityvirtual
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Although image-based virtual try-on has made considerable progress, emerging approaches still encounter challenges in producing high-fidelity and robust fitting images across diverse scenarios. These methods often struggle with issues such as texture-aware maintenance and size-aware fitting, which hinder their overall effectiveness. To address these limitations, we propose a novel garment perception enhancement technique, termed FitDiT, designed for high-fidelity virtual try-on using Diffusion Transformers (DiT) allocating more parameters and attention to high-resolution features. First, to further improve texture-aware maintenance, we introduce a garment texture extractor that incorporates garment priors evolution to fine-tune garment feature, facilitating to better capture rich details such as stripes, patterns, and text. Additionally, we introduce frequency-domain learning by customizing a frequency distance loss to enhance high-frequency garment details. To tackle the size-aware fitting issue, we employ a dilated-relaxed mask strategy that adapts to the correct length of garments, preventing the generation of garments that fill the entire mask area during cross-category try-on. Equipped with the above design, FitDiT surpasses all baselines in both qualitative and quantitative evaluations. It excels in producing well-fitting garments with photorealistic and intricate details, while also achieving competitive inference times of 4.57 seconds for a single 1024x768 image after DiT structure slimming, outperforming existing methods.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Layering Virtual Try-On

    cs.CV 2026-07 conditional novelty 7.0

    A two-stage diffusion pipeline and new benchmark let virtual try-on add, remove, or swap clothing layers while preserving inner layers, with SOTA results on the new LVTON benchmark and on VITON-HD/DressCode.

  2. CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation

    cs.CV 2026-07 accept novelty 7.0

    CtrlVTON recasts virtual try-on as mask-conditioned editing and introduces VIP-SAM for instance-level garment segmentation, beating proprietary editors on layout fidelity while matching garment quality.

  3. OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation

    cs.CV 2026-06 unverdicted novelty 7.0

    OrthoTryOn uses Orthogonal Subspace Projection on shared LoRA and Fisher-guided Negative Guidance to enable conflict-free unified fashion generation, outperforming task-specific models on benchmarks.

  4. DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport

    cs.CV 2026-05 unverdicted novelty 7.0

    DirectTryOn achieves state-of-the-art one-step virtual try-on performance by applying pure conditional transport, garment preservation loss, and self-consistency loss to straighten trajectories in pretrained generativ...

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

    cs.CV 2026-04 unverdicted novelty 7.0

    A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.

  6. Structure-Detail Decoupled Autoregressive Generation for Fast and High-Fidelity Virtual Try-On

    cs.CV 2026-07 conditional novelty 6.5

    STAR-VTON decouples latent VAR structure synthesis from pixel-space matching-based detail recovery, yielding faster high-fidelity virtual try-on than diffusion baselines.

  7. Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On

    cs.CV 2026-07 conditional novelty 6.0

    Oxygen-TryOn performs any-item, multi-reference virtual try-on via understanding-driven generation, reporting state-of-the-art scores on public and internal benchmarks.

  8. The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection

    cs.CV 2025-12 unverdicted novelty 6.0

    KeyTailor improves video virtual try-on realism by using instruction-guided keyframes to enhance garment details and background integrity in DiT models without major architectural changes.

  9. TAMF-VTON: Texture-Aware Mask-Free Virtual Try-On via High-Fidelity Image Synthesis

    cs.CV 2026-07 conditional novelty 5.0

    TAMF-VTON is a mask-free diffusion virtual try-on system using Mixture-of-Experts adapters and frequency-domain supervision, reporting SOTA results on VITON-HD and DressCode with multi-garment support.

  10. FitVTON: Fit-aware Virtual Try-On via Body-Garment Size Control

    cs.CV 2026-06 unverdicted novelty 5.0

    FitVTON introduces a fit-aware virtual try-on model using text prompts for size control, auxiliary garment/body mask prediction, and texture rectification to achieve better sizing accuracy on diverse bodies than prior...

  11. Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items

    cs.CV 2026-04 unverdicted novelty 4.0

    Tstars-Tryon 1.0 is a deployed virtual try-on system claiming high robustness, photorealism, multi-reference flexibility, and near real-time speed for diverse fashion items.

  12. Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items

    cs.CV 2026-04 unverdicted novelty 3.0

    Tstars-Tryon 1.0 is a robust, photorealistic virtual try-on system with multi-image support and near real-time speed, deployed at industrial scale on Taobao and accompanied by a released benchmark.