OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation

arXiv:2601.22725 · cs.CV, cs.AI · Submitted 2026-01-30 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-01-30

Updated: 2026-10-10

Comments: Accepted at NeurIPS 2026, Evaluations and Datasets Track

Code: https://github.com/RenxingIntelligence/OpenVTON-Bench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Alignment — 1× in this paper
• Clustering — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 10 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen2.5-VL Technical Report
• SAM 3: Segment Anything with Concepts
• VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization
• CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models
• CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal Concatenation
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Towards Multi-pose Guided Virtual Try-on Network
• StyleGAN-Human: A Data-Centric Odyssey of Human Generation
• VITON: An Image-based Virtual Try-on Network
• PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask
• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• TryOnGAN: Body-Aware Try-On via Layered Interpolation
• LLaVA-OneVision: Easy Visual Task Transfer
• Self-Improving VLM Judges Without Human Annotations
• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
• Ovis2.5 Technical Report
• Dress Code: High-Resolution Multi-Category Virtual Try-On
• LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
• IMAGDressing-v1: Customizable Virtual Dressing

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models