AI Paper Atlas

Research map / Benchmarks / VITON-HD unpaired

VITON-HD unpaired leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VITON-HD unpaired. Best FID: 7.89 (GarDiff, ECCV 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

VITON-HD unpaired · FID

10 papers, each with its best reported number for its own method; lower is better.

#FID ↓MethodPaperTopic
17.89GarDiff
Stable Diffusion 2.1
Improving Virtual Try-On with Garment-focused Diffusion Models
ECCV 2024 · Table 1
Editing and style transfer
28.04EARSB(SD)+H2G-UH/FH
CatVTON
Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling
CVPR 2025 · Table 1
Editing and style transfer
38.32RefTON+R/MFRefTon: Reference person shot assist virtual Try-on
CVPR 2026 · Table 1
Editing and style transfer
48.52Leffa
SD1.5
Learning Flow Fields in Attention for Controllable Person Image Generation
CVPR 2025 · Table 1
Editing and style transfer
58.521CCVTON
Flux.1 Fill dev
High-Fidelity Virtual Try-On beyond Paired Data Scarcity via Diffusion-based Cycle-Consistent Learning
CVPR 2026 · Table 1
Editing and style transfer
68.53D4-VTOND4-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On
ECCV 2024 · Table 1
Editing and style transfer
78.763CORAL (w L_CORAL)
FLUX.1-Fill-dev
Correpondence Alignment For Improved Virtual Try-On
NeurIPS 2026 · Table 1
Editing and style transfer
88.8178VTON-HandFit
StableDiffusion v1.5
VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding
CVPR 2025 · Table 1
Human pose estimation
99.015CatVTON (Inpainting)
Stable Diffusion v1.5 inpainting
CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models
ICLR 2025 · Quantitative comparison table
Fast diffusion sampling
109.9034PROMO
FLUX.1-dev
PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On
CVPR 2026 · Table 1
Editing and style transfer

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.