Mahmoud Afifi
Senior CV / ML Engineer at Apple
PhD in Computer Science
Email: m.3[last name][at]gmail[dot]com
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CV | Linkedin | Google Scholar | ResearchGate | GitHub | Mathworks | Twitter | Instagram
Embedded Files
اللهم اغفر لأبي وارحمه، وتجاوز عن سيئاته، واجعل قبره روضة من رياض الجنة -- O Allah, forgive my father and have mercy on him.
Experience
Experience
Computer Vision / Machine Learning / Camera Algorithms Engineer: Working with the Creativity Apps team on creative editing tools and experiences for Apple Creator Studio. Previously worked with the Camera ISP Algorithms team on white balance correction for iPhone cameras.
Staff Research Scientist / Research Intern: Worked on modular AI-based ISP that includes an AWB module, a cross-camera preference-aware WB, a modular neural photofinishing module, with the ability to embed raw data under 2 MB per image for unlimited post-rendering re-editing. As an intern, I worked on My Filters and developed AI-based color and exposure correction methods.
Camera Software Engineer / Research Intern: Worked on image color correction of Pixel cameras. Developed a spatially varying AWB framework, a chromaticity mapping for cross-camera transfer without calibration objects, and DEF for HDR-based illuminant estimation. Collaborated with the Gemini team on zero-shot image classification. As a student researcher, I developed C5 with the Gcam team.
Research
Research
My research focuses on low-level computer vision, computational photography, and image editing/stylization. Selected work is below; my full list of publications is available here.
Mahmoud Afifi, Zhongling Wang, Ran Zhang, and Michael S. Brown
SIGGRAPH Asia 2026
AI Center-Toronto, Samsung Electronics
Unlike most neural ISPs that treat the entire imaging pipeline as a single black-box network, we decompose the process into standard, interpretable, modular learning-based components. This design requires no manual tuning and enables easier debugging, seamless scaling, cross-camera generalization, and fine-grained customization. It also gives users complete control over every stage of the pipeline and supports unlimited post-editable re-rendering by storing compact raw data within the final image. In addition, it enables learning diverse picture styles with minimal memory overhead and integrates naturally with external image-processing functions.
Paper | Supplementary Materials | arXiv | Code & Executables | GPU-Accelerated Bilateral Solver | Video
Dongyoung Kim, Junyong Lee*, Abhijith Punnappurath*, Mahmoud Afifi*, Sangmin Han, Alex Levinshtein, and Michael S. Brown
ECCV 2026
27.5% acceptance rateAI Center-Toronto, Samsung Electronics
A diffusion-based method for generating realistic camera raw images. RawGen produces a latent representation of linear CIE XYZ images, conditioned on an sRGB image or a text prompt. The latent is decoded to CIE XYZ and mapped to arbitrary target camera raw spaces.
* Equal contribution
Paper | Supplementary Materials | arXiv | Project Page
Mahmoud Afifi, Ran Zhang, and Michael S. Brown
ECCV 2026
27.5% acceptance rateAI Center-Toronto, Samsung Electronics
A lightweight, learnable pre-processing pipeline that adapts camera raw images before standard JPEG compression using spatial-domain and optionally frequency-domain transforms. The operations are fully invertible, with parameters fitting within the JPEG file’s comment (COM) segment (<64 KB), enabling accurate reconstruction of the original raw image after JPEG decoding. This yields high-fidelity raw-to-JPEG storage with significant size reduction.
Paper | Supplementary Materials | arXiv | Code | Poster | Video
Mahmoud Afifi*, Luxi Zhao*, Abhijith Punnappurath, Mohamed A. Abdelsalam, Ran Zhang, and Michael S. Brown
ICCV 2025
24% acceptance rateAI Center-Toronto, Samsung Electronics
Timestamp and geolocation, combined with capture metadata, provide strong cues for estimating scene illuminants in smartphone camera white balancing. Our method leverages this data, along with color information, using a lightweight learnable model (~5K parameters) that runs efficiently on a flagship mobile DSP (0.25 ms) and CPU (0.80 ms), achieving high accuracy. We also introduce a large dataset (~3.2K raw images) from the S24 Ultra, containing ground-truth illuminants (neutral and user-preference-based) and capture metadata.
* Equal contribution
Paper | Supplementary Materials | arXiv | Code | Data | Patent Application
SaiKiran Tedla*, Junyong Lee*, Beixuan Yang, Mahmoud Afifi, and Michael S. Brown
ICCV 2025 (Highlight)
24% acceptance rateAI Center-Toronto, Samsung Electronics in collaboration with York University
A method for multispectral (MS) image demosaicing designed for dual-camera setups that leverages co-captured high-fidelity RGB images to guide the reconstruction of lower-fidelity MS images. We also provide a large dataset of paired RGB and MS mosaiced images with ground-truth demosaiced outputs.
* Equal contribution
Paper | Supplementary Materials | arXiv | Code | Data | Patent Application
Dongyoung Kim, Mahmoud Afifi, Dongyun Kim, Michael S. Brown, and Seon Joo Kim
ICCV 2025
24% acceptance rateAI Center-Toronto, Samsung Electronics in collaboration with Yonsei University
By leveraging pre-calibrated color correction matrices (CCMs) existing in camera ISPs, we generate a compact camera fingerprint embedding to adapt our method to new cameras. Our method achieves state-of-the-art performance in color constancy across diverse cameras, while remaining lightweight.
Paper | Supplementary Materials | arXiv | Project Page | Code | Patent Application
Artem Nikonorov*, Georgy Perevozchikov*, Andrei Korepanov, Nancy Mehta, Mahmoud Afifi, Egor Ershov, and Radu Timofte
ICCV 2025
24% acceptance rateIn collaboration with the University of Würzburg, Samara University, and IITP RAS
A color-matching framework that employs a hypernetwork to generate spatially adaptive weights for controlling KAN’s nonlinear splines. The method achieves state-of-the-art color matching between diverse source and target distributions in both supervised and unsupervised settings.
* Equal contribution
Abdelrahman Abdelhamed*, Mahmoud Afifi*, and Alec Go
arXiv, 2024
With some prompt engineering, multimodal LLMs (e.g., Gemini) can perform zero-shot image classification. However, they may not consistently produce accurate target dataset labels. Our approach leverages multimodal LLMs & cross-modal embedding encoders to produce initial class prediction feature & image description feature alongside image feature, improving zero-shot image classification accuracy without the need for dataset-specific prompts. Our method outperforms prior methods across various datasets, achieving a 6.8% increase in accuracy on ImageNet.
* Equal contribution
arXiv | Code & Data | Patent Application | Google Research Post
Mahmoud Afifi, Zhenhua Hu, and Liang Liang
ECCV 2024
27.9% acceptance rateUtilizing the chromatic distortion present between long and short exposure frames of HDR photography, we introduce a compact guiding feature for illuminant estimators. Processed by just ~300 learnable parameters, our method achieves results that match or surpass previous methods relying on thousands or even millions of parameters.
Paper | Supplementary Materials | arXiv | Poster | Patent Application
Georgy Perevozchikov, Nancy Mehta, Mahmoud Afifi, and Radu Timofte
ECCV 2024
27.9% acceptance rateIn collaboration with the University of Würzburg
Rawformer, an unsupervised Transformer-based encoder-decoder model for raw-to-raw mapping, enables the utilization of learnable camera ISP trained on a specific camera's raw images to render raw images taken by new cameras with different characteristics.
Mahmoud Afifi, Marcus A. Brubaker, and Michael S. Brown
WACV 2022
35% acceptance rateYork University
Mixed/single-illuminant scene white balancing does not necessarily require illuminant estimation. Instead, the problem could be bounded by a small set of predefined white-balance settings. Given that, we locally blend a set of small images rendered with different white-balance settings to generate the final corrected image.
Paper | Supplementary Materials | arXiv | Code & Data | Poster | Presentation | Talk | Patent
Abdullah Abuolaim, Mahmoud Afifi, and Michael S. Brown
WACV 2022
35% acceptance rateYork University
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. Generating high-quality DP views can be used for other DP-based applications, such as reflection removal.
PDF | Supplementary Materials | arXiv | Code & Dataset | Patent
Mahmoud Afifi, Jonathan T. Barron, Chloe LeGendre, Yun-Ta Tsai, and Francois Bleibel
ICCV 2021 (Oral Presentation)
25.9% acceptance rate | 3% oral presentation acceptance rateGoogle Research
A self-calibration method for cross-camera color constancy through the lens of transductive inference: additional (unlabeled) images are provided as input to the model at test time, which allows the model to calibrate itself to the spectral properties of the test-set camera during inference.
Paper | Supplementary Materials | arXiv | Code | Poster | Presentation | Presentation (PDF) | Talk | Google @ ICCV'21
Mahmoud Afifi, Marcus A. Brubaker, and Michael S. Brown
CVPR 2021
23.4% acceptance rateYork University
HistoGAN is the first work to control colors of GAN-generated images based on features derived directly from color histograms. Our method learns to transfer the color information encapsulated in histogram features to the colors of a GAN-generated images (HistoGAN) or real input images (ReHistoGAN). As color histograms provide an abstract representation of image color that is decoupled from spatial information, our HistoGAN and ReHistoGAN are less restrictive and suitable across arbitrary domains.
Paper | Supplementary Materials | arXiv | Code & Dataset | Colab (histogram loss) | Poster | Presentation | Talk
Mahmoud Afifi, Konstantinos G. Derpanis, Björn Ommer, and Michael S. Brown
CVPR 2021
23.4% acceptance rateSAIC, Samsung Research America in collaboration with Heidelberg University
A single coarse-to-fine deep learning model with adversarial training to correct both over- and under-exposed photographs.
Paper | Supplementary Materials | arXiv | Code & Dataset | Poster | Presentation | Talk | Samsung Research Post | Patent
Mahmoud Afifi, Abdelrahman Abdelhamed, Abdullah Abuolaim, Abhijith Punnappurath, and Michael S. Brown
TPAMI 2021
Impact factor: 20.8 (2023)York University
Learning accurate camera-rendering linearization gives a significant improvement for different computer vision tasks (e.g., denoising, deblurring, and image enhancement).
Paper | arXiv | Supplementary Materials | External Link | Code & Dataset
Mahmoud Afifi and Abdullah Abuolaim
BMVC 2021
York University
A semi-supervised method to map between two different camera-raw spaces. Training requires an unpaired set of images besides a very small set of paired images taken by these two camera models.
arXiv | Dataset | Presentation
Mahmoud Afifi and Michael S. Brown
CVPR 2020 (Oral Presentation)
22.1% acceptance rate | 5.7% oral presentation acceptance rateSAIC, Samsung Research America
A multi-task deep learning model for post-capture white-balance correction and editing
Paper | Supplementary Materials | arXiv | Code | Presentation | Talk | CVPR Daily Magazine | Samsung Research Post | Samsung Newsroom | Patent
Abhijith Punnappurath, Abdullah Abuolaim*, Mahmoud Afifi*, and Michael S. Brown
ICCP 2020
York University
A symmetry property of dual-pixel kernels for unsupervised depth estimation
* Equal contribution
Paper | Code & Dataset | Talk
Mahmoud Afifi and Michael S. Brown
CIC 2020 (Oral Presentation)
York University
A simple method to link the nonlinear white-balance correction functions, introduced in our CVPR'19 work, to the user's selected colors to allow interactive white-balance manipulation
arXiv | Code | Presentation
Atima Lui, Nyalia Lui, Mahmoud Afifi, and Ariadne Bazigos
US Patent 2020
My Nudest Inc
A system for analyzing user input, combining user's image(s) and query responses to provide tailored color outputs. Through color correction and comparison to predetermined color identifiers, it delivers accurate results and product recommendations.
Mahmoud Afifi and Michael S. Brown
ICCV 2019
25% acceptance rateYork University
Deep learning models can be fooled by white-balance errors and their accuracy can be improved by augmented images with different white-balance settings.
Paper | Supplementary Materials | arXiv | Project Page | Code | Colab
Mahmoud Afifi, Brian Price, Scott Cohen, and Michael S. Brown
CVPR 2019
25.2% acceptance rateYork University in collaboration with Adobe Research
The first work to directly address the problem of incorrectly white-balanced images; requires a small memory overhead and it is fast.
Paper | Project Page | Supplementary Materials | Demo | Video | Code | Dataset | Adobe Research Post | Patent
Mahmoud Afifi, Brian Price, Scott Cohen, and Michael S. Brown.
Eurographics 2019 (Short Papers)
York University in collaboration with Adobe Research
A fully automated image recoloring without the need for target/reference images
Paper | Project Page | External Link | Code | Supplementary Materials | Presentation | Fast-Forward Video | Adobe Research Post
Mahmoud Afifi and Michael S. Brown
BMVC 2019 (Oral Presentation)
28% acceptance rate | 5% oral presentation acceptance rateYork University
Learning a new canonical space in an unsupervised manner allows us to train a single deep model on multiple camera sensors and perform accurate illuminant estimation for images captured by new unseen camera sensors in the inference phase.
Paper | Project Page | Supplementary Materials | arxiv | Code | Presentation | Talk | Patent
Mahmoud Afifi, Abhijith Punnappurath, Abdelrahman Abdelhamed, Hakki Can Karaimer, Abdullah Abuolaim, and Michael S. Brown
CIC 2019 (Oral Presentation)
Best paper award
York University
With a small modification to existing camera ISPs, we can achieve accurate post-capture white balance editing by embedding a set of mapping coefficients in the JPEG metadata.
Paper | Project Page | Code | Presentation | Patent Application
Mahmoud Afifi and Abdelrahman Abdelhamed
JVCI 2019
Impact factor: 2.6 (2023)Assiut University
Gender classification can be improved using different facial features; a user study validates our finding.
Mahmoud Afifi
MTA 2019
Impact factor: 3.0 (2023)Assiut University
Hand images can be used for gender recognition and biometric identification; a large dataset of hand images enables us to train our two-stream deep model.
Abdullah Sawas*, Abdullah Abuolaim*, Mahmoud Afifi, and Manos Papagelis
MDM 2018
Best paper award
York University
Efficient discovery of evolving groups of pedestrians; a new group pattern is introduced in the journal version.
* Equal contribution
Mahmoud Afifi and Khaled F. Hussain
CVM 2015
Impact factor: 17.3 (2023)Assiut University
Bleeding artifacts caused by Poisson image editing can be reduced by a simple two-stage blending approach.
Paper | Project Page | Code | Video
Conference version: Paper | Project Page | Code | Video
Mahmoud Afifi, Khaled F. Hussain, Hosny M. Ibrahim, and Nagwa M. Omar
ISPACS 2014
Assiut University
In many scenarios, image registration and blending can help to get a fast video completion.
Honors
Honors
Dissertation Award
CS-Can|Info-Can Canadian Computer Science Distinguished Dissertation Award, 2021 | Lassonde post
CIPPRS John Barron Doctoral Dissertation Award, 2021 | Lassonde post
Nominated by EECS for the Best Doctoral Dissertation Prize at York University, 2021
Best Paper Award
Outstanding Reviewer
European Conference on Computer Vision, 2026 (ECCV'26)
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026 (CVPR'26)
IEEE/CVF International Conference on Computer Vision, 2025 (ICCV'25)
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025 (CVPR'25)
European Conference on Computer Vision, 2024 (ECCV'24)
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024 (CVPR'24)
IEEE/CVF International Conference on Computer Vision, 2021 (ICCV'21)
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020 (CVPR'20)
Honourable Mention at British Machine Vision Conference, 2019 (BMVC'19)
Challenges
Runner-Up Award overall tracks in AIM 2020 Challenge on Scene Relighting and Illumination Estimation at ECCV'20
Best Short CG Film in the Fourth Forum of Egyptian Faculties of Computer and Information Science, 2010
Others
Professional Services
Professional Services
Google Advocate for the African Computer Vision Summer School (ACVSS) in Kenya, 2024
Program Committee Member:
NTIRE: New Trends in Image Restoration and Enhancement workshop and challenges in conjunction with CVPR 2026
AIM: Advances in Image Manipulation workshop in conjunction with ICCV 2025
NTIRE: New Trends in Image Restoration and Enhancement workshop and challenges in conjunction with CVPR 2025
AIM: Advances in Image Manipulation workshop in conjunction with ECCV 2024
NTIRE: New Trends in Image Restoration and Enhancement workshop and challenges in conjunction with CVPR 2024
NTIRE: New Trends in Image Restoration and Enhancement workshop and challenges in conjunction with CVPR 2023
NTIRE: New Trends in Image Restoration and Enhancement workshop and challenges in conjunction with CVPR 2022 | Apple post
NTIRE: New Trends in Image Restoration and Enhancement workshop and challenges in conjunction with CVPR 2020
Student Representative at Tenure & Promotion Adjudicating Committee, EECS, York University, 2020
Reviewer:
Conferences: ECCV'26, CVPR'26, WACV'26, ICCV'25, CVPR'25, ECCV'24, CVPR'24, ACCV'24, LIM'24, SIGGRAPH Asia'23, ICCV'23, CVPR'23, SIGGRAPH Asia'22, CVPR'22, WACV'22, SIGGRAPH Asia'21, SIGGRAPH'21, ICCV'21, CVPR'21, BMVC'21, WACV'21, MASCOTS'21, CVPR'20, WACV'20, ACCV'20, MASCOTS'20, CIC28, CRV'20, WACV'19, CIC27, BMVC'19, BMVC'18
Journals: T-PAMI, T-IP, IJCV, T-CI, T-MM, CVM, VTM, T-ITS, T-CSVT, T-HMS, T-MECH, T-CE, Neurocomputing, IEEE Access, TOMM, TVCJ, MTAP, COL, Displays, JVCI, MULT, MVAP, SIVP, JRTIP, IET IP, IET CV, IET SP, IET EL, SPIE JEI, CIN, JHE, OPENCS
Vice-Chair: ACM Assiut Student Chapter
Page updated
Google Sites
Report abuse