Unsupervised Image Restoration

Latest papers

8 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

TriINR: Unsupervised Atmospheric Turbulence Mitigation with Triple Implicit Neural Representations
Oct 16, 2026Yuka Ogino, Rikuto Otsuka, Yuho Shoji +3Unsupervised Image Restoration Atmospheric Turbulence Mitigation
NEC Corporation, Japan
Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal
Oct 1, 2026Cap Dang Xuan Kiet, Tat-Jen ChamUnsupervised Image Restoration All-in-One Image Restoration
College of Computing and Data Science, Nanyang Technological University, Singapore
BiDeMem: Bidirectional Degradation Memory for Explainable Image Restoration
Jun 26, 2026Xinrui Wu, Lichen HuangMemory-Augmented Neural Networks Unsupervised Image Restoration
University of Electronic Science and Technology of China
RQUL-UIE: Revitalizing Quality-Unstable Labels for Underwater Image Enhancement via In-Dataset Self-Supervision
Jun 4, 2026Haochen Hu, Yanrui Bin, Chih-yung Wen +1Diffusion Models for Image Restoration Unsupervised Image Restoration
1The Hong Kong Polytechnic University
Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions
May 23, 2026Ziyan Huang, Lang Wu, Hongji Wang +3Unsupervised Image Restoration Image Deblurring
School of Mathematics and Statistics, Central South University, Changsha, 410083, People’s Republic of China · Key Laboratory for Micro/Nano Optoelectronic Devices of Ministry of Education, Hunan Provincial Key Laboratory of Low-Dimensional Structural Physics and Devices, School of Physics and Electronics, Hunan University, Changsha 410082, People’s Republic of China
Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
May 1, 2026Yinghao Chen, Yeying Jin, Xiang Chen +3Unsupervised Image Restoration Self-Training
1National University of Defense Technology · National University of Singapore · 3Nanjing University of Science and Technology +2
Diffusion Autoencoder for Unsupervised Artifact Restoration in Handheld Fundus Images
Apr 17, 2026Mathumetha Palani, Kavya Puthumana, Ayantika Das +1Diffusion Models for Image Restoration Unsupervised Image Restoration
Nuvo AI, Chennai, India · Indian Institute of Technology Madras, India
Looking Into the Water by Unsupervised Learning of the Surface Shape
Mar 8, 2026Ori Lifschitz, Tali Treibitz, Dan RosenbaumUnsupervised Image Restoration Image Restoration
Hatter Department of Marine Technologies, Charney School of Marine Sciences, University of Haifa, Haifa, Israel · Department of Computer Science, University of Haifa, Haifa, Israel

Oct 16, 2026J/K move · Enter open · S save

TriINR: Unsupervised Atmospheric Turbulence Mitigation with Triple Implicit Neural Representations

Yuka Ogino, Rikuto Otsuka, Yuho Shoji, Takuya Ogawa+2

NEC Corporation, Japan

Unsupervised Image Restoration Atmospheric Turbulence Mitigation Image Restoration Image Deblurring Implicit Neural Representations Physics-Guided Image Restoration

Open paper AskPDF arXiv

Atmospheric turbulence degrades image quality in long-range imaging. The degradation is generally modeled with two spatio-temporally varying components, tilt and blur. Recent unsupervised turbulence mitigation methods have demonstrated the effectiveness of representing a sharp image as an implicit neural representation (INR). However, their tilt and blur representations remain frame-dependent, and the number of optimization parameters grows with the number of input frames. To address this limitation, we propose TriINR, an unsupervised turbulence mitigation method that recovers a sharp image from multiple degraded frames. TriINR represents the sharp image, tilt, and blur as three implicit neural representations. By modeling tilt and blur as spatio-temporal INRs, TriINR achieves frame-count-independent degradation representation and memory-efficient optimization. We further incorporate physical and statistical properties of atmospheric turbulence as constraints on the INRs to improve restoration accuracy. Experiments on synthesized turbulence data with three degradation strengths show that TriINR restores images more robustly across varying turbulence strengths than prior TM methods and achieves the highest accuracy among the evaluated unsupervised methods. Our method also demonstrates robustness on real long-range scenes containing additional non-ideal motion.