AI Paper Atlas

Research map / Benchmarks / VITON-HD

VITON-HD leaderboard

22 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VITON-HD. Best SSIM: 0.928 (Ours (two-stage), ECCV 2026).

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 · SSIM

19 papers, each with its best reported number for its own method; higher is better.

9 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

VITON-HD · FID

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

#FID ↓MethodPaperTopic
15.12IEC
Kontext-dev 12B VTO
When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training
ECCV 2026 · Table 6
RL from feedback
25.9564VTON-HandFit
StableDiffusion v1.5
VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding
CVPR 2025 · Table 3
Human pose estimation
36.062CDM-VTONCascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution
AAAI 2025 · Table 1
Editing and style transfer
46.29IDM-VTON
SDXL inpainting
Improving Diffusion Models for Authentic Virtual Try-on in the Wild
ECCV 2024 · Table 1
Editing and style transfer
58.155Wear-Any-Way
Stable Diffusion 1.5
Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignment
ECCV 2024 · Table 3
Editing and style transfer
68.54Ours (TPD)
Stable Diffusion
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On
CVPR 2024 · Table 1
Editing and style transfer
78.6OOTD + TryOn-Refiner
OOTD
TryOn-Refiner: Conditional Rectified-flow-based TryOn Refiner for More Accurate Detail Reconstruction
ICCV 2025 · Table 1
Image restoration
88.6AnyFit
SDXL
AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
NeurIPS 2024 · Table 1
Editing and style transfer
98.67WildVidFit
Stable Diffusion
WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models
ECCV 2024 · Table 1
Video generation
108.71TEMU-VTOFFInverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals
ICLR 2026 · Table 2
Editing and style transfer
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

VITON-HD · LPIPS

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

#LPIPS ↓MethodPaperTopic
10.047IEC
Kontext-dev 12B VTO
When Rubrics Fail: Error Enumeration as Reward for Reference-Free RL Post-Training
ECCV 2026 · Table 6
RL from feedback
20.047FIA-VTON (Ours)Learning Implicit Features with Flow-Infused Transformations for Realistic Virtual Try-On
ICCV 2025 · Table 1
Editing and style transfer
30.048SAL-VTONLinking Garment With Person via Semantically Associated Landmarks for Virtual Try-On
CVPR 2023 · Table 1
Recognition and long-tail
40.061Ours
StableDiffusion v1.4
Latent Diffusion-Enhanced Virtual Try-On via Optimized Pseudo-Label Generation
AAAI 2025 · Table 2
Editing and style transfer
50.063SDXL-TryOn + TryOn-Refiner
SDXL-TryOn
TryOn-Refiner: Conditional Rectified-flow-based TryOn Refiner for More Accurate Detail Reconstruction
ICCV 2025 · Table 2
Image restoration
60.0636CDM-VTONCascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution
AAAI 2025 · Table 1
Editing and style transfer
70.07GarFastGarFast: Realistic and Fast Garment Transfer with a Simplified Parser-Free Approach
AAAI 2025 · Table 3
Editing and style transfer
80.07Ours (TPD)
Stable Diffusion
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On
CVPR 2024 · Table 1
Editing and style transfer
90.071OOTDiffusion
Stable Diffusion v1.5
OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On
AAAI 2025 · Quantitative results on VITON-
Editing and style transfer
100.075AnyFit
SDXL
AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
NeurIPS 2024 · Table 1
Editing and style transfer
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

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