Realistic Compound-Lens Defocus Blur Synthesis

• URL: http://arxiv.org/abs/2607.05837v1
• Date: Tue, 07 Jul 2026 05:00:44 GMT
• Title: Realistic Compound-Lens Defocus Blur Synthesis
• Abstract summary: We propose a pipeline for synthesizing realistic defocus deblurring datasets for diverse compound lenses.<n>We generate CLDefocus, a large-scale synthetic dataset containing lens-diverse defocus image pairs.
• Score: 16.115267588640453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learning deblurring methods have achieved strong performance, their effectiveness depends on training data and often degrades across cameras and lenses due to limited optical diversity and realism in existing datasets. In this paper, we propose a pipeline for synthesizing realistic defocus deblurring datasets for diverse compound lenses. It integrates efficient wave-optics PSF computation via Debye CZT propagation, depth-aware defocus rendering with occlusion handling, and blur synthesis in the radiometrically linear space with camera ISP simulation. This unified pipeline enables the scalable generation of photorealistic defocus datasets with diverse lens characteristics. Using our pipeline, we generate CLDefocus, a large-scale synthetic dataset containing lens-diverse defocus image pairs. We further analyze the limitations of real-captured defocus datasets and show that such imperfections can bias full-reference evaluation. Extensive experiments demonstrate that models trained on CLDefocus achieve improved cross-device generalization compared to models trained on existing real and synthetic datasets.

Related papers

• DefocusTrackerAI -- A Generalized Framework for the Automatic Detection of Defocused Particle Images [0.0]
  DefocusTrackerAI is a framework for the automatic detection and position estimation of defocused particle images.<n>YOLOv9 is trained on a diverse and feature-rich synthetic image set containing astigmatic and non-astigmatic defocused particle images of varying diameters.
  arXiv  Detail & Related papers  (2026-05-22T08:01:22Z)
• Learning to Remove Lens Flare in Event Camera [56.9171469873838]
  We present E-DeflareDeflare, the first framework for removing lens flare from event camera data.<n>We first establish the theoretical foundation by deriving a physics-grounded forward model of the non-linear suppression mechanism.<n> Empowered by this benchmark, we design E-DeflareNet, which achieves state-of-the-art restoration performance.
  arXiv  Detail & Related papers  (2025-12-09T18:59:57Z)
• Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites [9.308179344001795]
  Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes.<n>Existing pipelines often rely on camera parameters to compute the circle of confusion (CoC) for realistic lens blur rendering.<n>We propose a novel approach that directly estimates the CoC map from RGB images, bypassing the need for scene depth or camera metadata.
  arXiv  Detail & Related papers  (2025-11-21T07:32:05Z)
• Fine-grained Defocus Blur Control for Generative Image Models [66.30016220484394]
  Current text-to-image diffusion models excel at generating diverse, high-quality images.<n>We introduce a novel text-to-image diffusion framework that leverages camera metadata.<n>Our model enables superior fine-grained control without altering the depicted scene.
  arXiv  Detail & Related papers  (2025-10-07T17:59:15Z)
• Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur [16.9629875455607]
  Deep learning models trained on existing open-source datasets often face domain gaps and do not perform well in real-world settings.<n>We propose an efficient and scalable dataset approach that does not rely on fine-tuning with real-world data.<n>Our method simultaneously models depth-dependent defocus and spatially varying optical aberrations, addressing both computational complexity and the scarcity of high-quality RGB-D datasets.
  arXiv  Detail & Related papers  (2025-07-01T02:03:04Z)
• LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction [32.85180149439811]
  Lensless imaging stands out as a promising alternative to conventional lens-based systems.<n>Traditional lensless techniques often require explicit calibrations and extensive pre-processing.<n>We propose LensNet, an end-to-end deep learning framework that integrates spatial-domain and frequency-domain representations.
  arXiv  Detail & Related papers  (2025-05-03T09:11:52Z)
• Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models [58.98742597810023]
  Vision models have to behave in a robust way to disturbances such as noise or blur.<n>This paper studies two datasets of blur corruptions, which we denote OpticsBench and LensCorruptions.<n> Evaluations for image classification and object detection on ImageNet and MSCOCO show that for a variety of different pre-trained models, the performance on OpticsBench and LensCorruptions varies significantly.
  arXiv  Detail & Related papers  (2025-04-25T17:23:47Z)
• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space [3.097163558730473]
  We train autoencoders with implicit and explicit regularization techniques to enforce linearity relations. Compared to existing works, we use a simple architecture to synthesize images with flexible blur levels. Our regularized autoencoders can effectively mimic blur and deblur, increasing data variety as a data augmentation technique.
  arXiv  Detail & Related papers  (2023-07-28T10:27:28Z)
• Towards Real-World Video Deblurring by Exploring Blur Formation Process [53.91239555063343]
  In recent years, deep learning-based approaches have achieved promising success on video deblurring task. The models trained on existing synthetic datasets still suffer from generalization problems over real-world blurry scenarios. We propose a novel realistic blur synthesis pipeline termed RAW-Blur by leveraging blur formation cues.
  arXiv  Detail & Related papers  (2022-08-28T09:24:52Z)
• Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution [51.274657266928315]
  We propose a PSF aware plug-and-play deep network, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating lens-specific deep priors. Specifically, we pre-train a base model from a set of diverse lenses and then adapt it to a given lens by quickly refining the parameters.
  arXiv  Detail & Related papers  (2021-04-07T12:00:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.