PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model
Xiang Gao, Shuai Yang, Jiaying Liu
Abstract
cn "forest path, painting" "ruins" "laboratory" "harbor, oil painting" "stones" "leaves" reference "desert" "music room, painting" * Corresponding author. asynchronous phase transfer to enable flexible control over the degree of hidden content discernability. Our method bypasses any model training and fine-tuning process, all while substantially outperforming related methods in image quality, text fidelity, visual discernibility, and contextual naturalness for illusion picture synthesis, as demonstrated by extensive qualitative and quantitative experiments. Our
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext de5638f1-13bf-4ab5-b51c-3c6260c3fac5Cited by top-tier papers3
- Stroke of Surprise: Progressive Semantic Illusions in Vector SketchingHuai-Hsun Cheng, Siang-Ling Zhang, Yu-Lun LiuSIGGRAPH 2026 · 1 citation
- Steering Where to Diffuse: Generative Modeling of Phenotypic Response Simulation with Steered Diffusion BridgeRongchao Zhang, Chengxin Li, Yiwei Lou, Yuling Shi et al.CVPR 2026 · 1 citation
- Text-guided Controllable Diffusion for Realistic Camouflage Images GenerationYuhang Qian, Haiyan Chen, Wentong Li, Ningzhong Liu et al.AAAI 2026 · 1 citation
Builds on28
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
Related papers
- IFCSR: Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-ResolutionJonghee Back, Jongju Kim, Jeong-Uk Kim, Eunjin Kim et al.CVPR 2026
- Inversion-based Style Transfer with Diffusion ModelsYuxin Zhang, Nisha Huang, Fan Tang, Haibin Huang et al.CVPR 2023
- OmniStyle: Filtering High Quality Style Transfer Data at ScaleYe Wang, Ruiqi Liu, Jiang Lin, Fei Liu et al.CVPR 2025
- Zero-Shot Generative Model Adaptation via Image-Specific Prompt LearningJiayi Guo, Chaofei Wang, You Wu, Eric J. Zhang et al.CVPR 2023
- NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial TrainingDar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou, Yi-Zhe SongCVPR 2025
