36 skills found · Page 1 of 2
subeeshvasu / Awesome DeblurringA curated list of resources for Image and Video Deblurring
codeslake / IFAN[CVPR 2021] Official PyTorch Implementation for "Iterative Filter Adaptive Network for Single Image Defocus Deblurring"
Abdullah-Abuolaim / Defocus Deblurring Dual PixelReference github repository for the paper "Defocus Deblurring Using Dual-Pixel Data". We introduce a deep neural network (DNN) architecture that uses the dual-pixel (DP) sub-aperture views to reduce defocus blur.
codeslake / DMENet[CVPR 2019] Official TensorFlow Implementation for "Deep Defocus Map Estimation using Domain Adaptation"
lingyanruan / DRBNet[CVPR Oral 2022] PyTorch Implementation for "Learning to Deblur using Light Field Generated and Real Defocused Images"
atfortes / BokehDiffusion[SIGGRAPH Asia 2025] Official code for "Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models."
vinthony / Depth Distillation[ECCV 2020] Defocus Blur Detection via Depth Distillation
xinario / Defocus SegmentationLBP-based segmentation of defocus blur
panda5mt / Depth Estimate BlurDefocusによる画像ボケを利用した深度推定
TimSeizinger / Bokehlicious[ICCV 2025 Highlight] Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures. Official Code and Dataset
Abdullah-Abuolaim / Recurrent Defocus Deblurring Synth Dual PixelReference github repository for the paper "Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data". We propose a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Leveraging these realistic synthetic DP images, we introduce a new recurrent convolutional network (RCN) architecture that can improve defocus deblurring results and is suitable for use with single-frame and multi-frame data captured by DP sensors.
Abdullah-Abuolaim / Multi Task Defocus Deblurring Dual Pixel NimatReference github repository for the paper "Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning". We propose a single-image deblurring network that incorporates the two sub-aperture views into a multitask framework. Specifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the network’s ability to learn to deblur the image. Our experiments show this multi-task strategy achieves +1dB PSNR improvement over state-of-the-art defocus deblurring methods. In addition, our multi-task framework allows accurate DP-view synthesis (e.g., ~ 39dB PSNR) from the single input image. These high-quality DP views can be used for other DP-based applications, such as reflection removal. As part of this effort, we have captured a new dataset of 7,059 high-quality images to support our training for the DP-view synthesis task.
yuxinjin-whu / D DFFNetDepth and DOF Cues Make A Better Defocus Blur Detector
complight / Realistic Defocus:cyclone: Realistic defocus blur for Multiplane Computer-Generated Holography
shangcai1 / SGCVPR2021:Self-generated Defocus Blur Detection via Dual Adversarial Discriminators
rongduo / DOFGS Implementation[CVPR2025]DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Refocusing, Defocus Rendering and Blur Removal
CattleProdigy / Image Blur MapA reproduction of the results of 'Estimating Spatially Varying Defocus Blur From A Single Image' by Zhu et. al.
wdzhao123 / APLECCV2022: United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning
sahitpj / Wiener FilterUsing A variant of a Wiener filter as an Image restoration technique for Gaussian and Defocus Blur
alikaraali / Edge Based Dfe Tip2018A. Karaali, CR. Jung, "Edge-Based Defocus Blur Estimation with Adaptive Scale Selection", IEEE Transactions on Image Processing (TIP 2018), 2018
