Search Results for author: Michael S. Brown

Found 52 papers, 25 papers with code

Examining Autoexposure for Challenging Scenes

no code implementations ICCV 2023 SaiKiran Tedla, Beixuan Yang, Michael S. Brown

While current AE algorithms are effective in well-lit environments with constant illumination, these algorithms still struggle in environments with bright light sources or scenes with abrupt changes in lighting.

NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement

1 code implementation20 Jun 2023 Marcos V. Conde, Javier Vazquez-Corral, Michael S. Brown, Radu Timofte

Moreover, a NILUT can be extended to incorporate multiple styles into a single network with the ability to blend styles implicitly.

Color Manipulation Photo Retouching +1

GamutMLP: A Lightweight MLP for Color Loss Recovery

no code implementations CVPR 2023 Hoang M. Le, Brian Price, Scott Cohen, Michael S. Brown

Inspired by neural implicit representations for 2D images, we propose a method that optimizes a lightweight multi-layer-perceptron (MLP) model during the gamut reduction step to predict the clipped values.

Physically-Plausible Illumination Distribution Estimation

1 code implementation ICCV 2023 Egor Ershov, Vasily Tesalin, Ivan Ermakov, Michael S. Brown

Motivated by this observation, we revisit AWB to predict a distribution of plausible illuminations for use in white balance.

Graphics2RAW: Mapping Computer Graphics Images to Sensor RAW Images

no code implementations ICCV 2023 Donghwan Seo, Abhijith Punnappurath, Luxi Zhao, Abdelrahman Abdelhamed, Sai Kiran Tedla, Sanguk Park , Jihwan Choe, Michael S. Brown

The narrowing domain gap between real and synthetic imagery makes it possible to use CG images as training data for deep learning models targeting high-level computer vision tasks, such as autonomous driving and semantic segmentation.

Autonomous Driving Denoising +2

MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning

no code implementations16 Nov 2022 Shuwei Li, Jikai Wang, Michael S. Brown, Robby T. Tan

To have better cues of the local surface/light colors under multiple light color conditions, we design a novel multi-task learning framework.

Color Constancy Edge Detection +1

Day-to-Night Image Synthesis for Training Nighttime Neural ISPs

1 code implementation CVPR 2022 Abhijith Punnappurath, Abdullah Abuolaim, Abdelrahman Abdelhamed, Alex Levinshtein, Michael S. Brown

Training nightmode ISP networks relies on large-scale datasets of image pairs with: (1) a noisy raw image captured with a short exposure and a high ISO gain; and (2) a ground truth low-noise raw image captured with a long exposure and low ISO that has been rendered through the ISP.

Image Generation

Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata

1 code implementation CVPR 2022 Seonghyeon Nam, Abhijith Punnappurath, Marcus A. Brubaker, Michael S. Brown

Our experiments show that our learned sampling can adapt to the image content to produce better raw reconstructions than existing methods.

Raw reconstruction

Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images

1 code implementation CVPR 2022 Ali Maleky, Shayan Kousha, Michael S. Brown, Marcus A. Brubaker

This paper proposes a framework for training a noise model and a denoiser simultaneously while relying only on pairs of noisy images rather than noisy/clean paired image data.

Denoising Density Estimation

Modeling sRGB Camera Noise with Normalizing Flows

no code implementations CVPR 2022 Shayan Kousha, Ali Maleky, Michael S. Brown, Marcus A. Brubaker

The nonlinear steps on the ISP culminate in a significantly more complex noise distribution in the sRGB domain and existing raw-domain noise models are unable to capture the sRGB noise distribution.

Denoising

Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels

3 code implementations15 Nov 2021 Abdullah Abuolaim, Mahmoud Afifi, Michael S. Brown

In this work, we follow the trend of rendering the NIMAT effect by introducing a modification on the blur synthesis procedure in portrait mode.

Attribute Motion Synthesis

Auto White-Balance Correction for Mixed-Illuminant Scenes

1 code implementation17 Sep 2021 Mahmoud Afifi, Marcus A. Brubaker, Michael S. Brown

Auto white balance (AWB) is applied by camera hardware at capture time to remove the color cast caused by the scene illumination.

Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning

1 code implementation11 Aug 2021 Abdullah Abuolaim, Mahmoud Afifi, Michael S. Brown

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.

Deblurring Depth Estimation +4

Neural Image Representations for Multi-Image Fusion and Layer Separation

no code implementations2 Aug 2021 Seonghyeon Nam, Marcus A. Brubaker, Michael S. Brown

We propose a framework for aligning and fusing multiple images into a single view using neural image representations (NIRs), also known as implicit or coordinate-based neural representations.

Optical Flow Estimation

CAMS: Color-Aware Multi-Style Transfer

1 code implementation26 Jun 2021 Mahmoud Afifi, Abdullah Abuolaim, Mostafa Hussien, Marcus A. Brubaker, Michael S. Brown

A nice feature of our method is that it enables the users to manually select the color associations between the target style and content image for more transfer flexibility.

Style Transfer

Leveraging the Availability of Two Cameras for Illuminant Estimation

no code implementations CVPR 2021 Abdelrahman Abdelhamed, Abhijith Punnappurath, Michael S. Brown

In this paper, we leverage the availability of these two cameras for the task of illumination estimation using a small neural network to perform the illumination prediction.

Vocal Bursts Valence Prediction

Mobile Computational Photography: A Tour

no code implementations17 Feb 2021 Mauricio Delbracio, Damien Kelly, Michael S. Brown, Peyman Milanfar

The first mobile camera phone was sold only 20 years ago, when taking pictures with one's phone was an oddity, and sharing pictures online was unheard of.

Super-Resolution

Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data

1 code implementation ICCV 2021 Abdullah Abuolaim, Mauricio Delbracio, Damien Kelly, Michael S. Brown, Peyman Milanfar

Leveraging these realistic synthetic DP images, we introduce a recurrent convolutional network (RCN) architecture that improves deblurring results and is suitable for use with single-frame and multi-frame data (e. g., video) captured by DP sensors.

Ranked #13 on Image Defocus Deblurring on DPD (Dual-view) (using extra training data)

Deblurring Image Defocus Deblurring

HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms

1 code implementation CVPR 2021 Mahmoud Afifi, Marcus A. Brubaker, Michael S. Brown

This goal has led to significant interest in methods that can intuitively control the appearance of images generated by GANs.

Image Generation

Interactive White Balancing for Camera-Rendered Images

1 code implementation26 Sep 2020 Mahmoud Afifi, Michael S. Brown

This is because RAW images have no photo-rendering operations applied and photo-editing software is able to apply WB and other photo-finishing procedures to render the final image.

A Little Bit More: Bitplane-Wise Bit-Depth Recovery

1 code implementation3 May 2020 Abhijith Punnappurath, Michael S. Brown

Imaging sensors digitize incoming scene light at a dynamic range of 10--12 bits (i. e., 1024--4096 tonal values).

Quantization

Defocus Deblurring Using Dual-Pixel Data

1 code implementation ECCV 2020 Abdullah Abuolaim, Michael S. Brown

DP sensors are used to assist a camera's auto-focus by capturing two sub-aperture views of the scene in a single image shot.

Deblurring Image Defocus Deblurring

Deep White-Balance Editing

4 code implementations CVPR 2020 Mahmoud Afifi, Michael S. Brown

The ISP rendering begins with a white-balance procedure that is used to remove the color cast of the scene's illumination.

What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance

1 code implementation ICCV 2019 Mahmoud Afifi, Michael S. Brown

There is active research targeting local image manipulations that can fool deep neural networks (DNNs) into producing incorrect results.

Color Constancy Image Augmentation +3

Sensor-Independent Illumination Estimation for DNN Models

1 code implementation14 Dec 2019 Mahmoud Afifi, Michael S. Brown

Our learned space retains the linear property of the original sensor raw-RGB space and allows unseen camera sensors to be used on a single DNN model trained on this working space.

As-projective-as-possible bias correction for illumination estimation algorithms

1 code implementation JOSA A 2019 Mahmoud Afifi, Abhijith Punnappurath, Graham Finlayson, Michael S. Brown

Recent work by Finlayson, Interface Focus, 2018 showed that a bias correction function can be formulated as a projective transform because the magnitude of the R, G, B illumination vector does not matter to the AWB procedure.

Revisiting Autofocus for Smartphone Cameras

no code implementations ECCV 2018 Abdullah Abuolaim, Abhijith Punnappurath, Michael S. Brown

The fact that different objectives exist raises the research question of whether there is a preferred objective.

A High-Quality Denoising Dataset for Smartphone Cameras

no code implementations CVPR 2018 Abdelrahman Abdelhamed, Stephen Lin, Michael S. Brown

We propose a systematic procedure for estimating ground truth for noisy images that can be used to benchmark denoising performance for smartphone cameras.

Image Denoising Vocal Bursts Intensity Prediction

Classification-Driven Dynamic Image Enhancement

no code implementations CVPR 2018 Vivek Sharma, Ali Diba, Davy Neven, Michael S. Brown, Luc van Gool, Rainer Stiefelhagen

In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception.

Classification General Classification +3

Improving Color Reproduction Accuracy on Cameras

no code implementations CVPR 2018 Hakki Can Karaimer, Michael S. Brown

In this paper, we discuss the limitations of the current colorimetric mapping approach and propose two methods that are able to improve color accuracy.

Classification Driven Dynamic Image Enhancement

no code implementations20 Oct 2017 Vivek Sharma, Ali Diba, Davy Neven, Michael S. Brown, Luc van Gool, Rainer Stiefelhagen

In this paper, we are interested in learning CNNs that can emulate image enhancement and restoration, but with the overall goal to improve image classification and not necessarily human perception.

Classification General Classification +3

A Non-Local Low-Rank Framework for Ultrasound Speckle Reduction

no code implementations CVPR 2017 Lei Zhu, Chi-Wing Fu, Michael S. Brown, Pheng-Ann Heng

`Speckle' refers to the granular patterns that occur in ultrasound images due to wave interference.

Why You Should Forget Luminance Conversion and Do Something Better

no code implementations CVPR 2017 Rang M. H. Nguyen, Michael S. Brown

One of the most frequently applied low-level operations in computer vision is the conversion of an RGB camera image into its luminance representation.

Haze Visibility Enhancement: A Survey and Quantitative Benchmarking

no code implementations21 Jul 2016 Yu Li, ShaoDi You, Michael S. Brown, Robby T. Tan

This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes.

Benchmarking

Two Illuminant Estimation and User Correction Preference

no code implementations CVPR 2016 Dongliang Cheng, Abdelrahman Abdelhamed, Brian Price, Scott Cohen, Michael S. Brown

Existing methods attempt to estimate a spatially varying illumination map, however, results are error prone and the resulting illumination maps are too low-resolution to be used for proper spatially varying white-balance correction.

Vocal Bursts Valence Prediction

Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras

no code implementations CVPR 2016 Seoung Wug Oh, Michael S. Brown, Marc Pollefeys, Seon Joo Kim

In particular, due to the differences in spectral sensitivities of the cameras, different cameras yield different RGB measurements for the same spectral signal.

SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs

no code implementations ICCV 2015 Yu Li, Dongbo Min, Michael S. Brown, Minh N. Do, Jiangbo Lu

However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint.

Optical Flow Estimation

Nighttime Haze Removal With Glow and Multiple Light Colors

no code implementations ICCV 2015 Yu Li, Robby T. Tan, Michael S. Brown

We demonstrate the effectiveness of our nighttime haze model and correction method on a number of examples and compare our results with existing daytime and nighttime dehazing methods' results.

Beyond White: Ground Truth Colors for Color Constancy Correction

no code implementations ICCV 2015 Dongliang Cheng, Brian Price, Scott Cohen, Michael S. Brown

A limitation in color constancy research is the inability to establish ground truth colors for evaluating corrected images.

Color Constancy

Effective Learning-Based Illuminant Estimation Using Simple Features

no code implementations CVPR 2015 Dongliang Cheng, Brian Price, Scott Cohen, Michael S. Brown

More recent state-of-the-art methods employ learning-based techniques that produce better results, but often rely on complex features and have long evaluation and training times.

Color Constancy

Illuminant Aware Gamut-Based Color Transfer

1 code implementation Pacific Graphics 2014 Rang Nguyen, Seon Joo Kim, Michael S. Brown

Our method is unique in its considera- tion of the scene illumination and the constraint that the mapped image must be within the color gamut of the target image.

Raw-to-Raw: Mapping between Image Sensor Color Responses

no code implementations CVPR 2014 Rang Nguyen, Dilip K. Prasad, Michael S. Brown

We show that this approach achieves state-of-the-art results on a range of consumer cameras and images of arbitrary scenes and illuminations.

As-Projective-As-Possible Image Stitching with Moving DLT

no code implementations CVPR 2013 Julio Zaragoza, Tat-Jun Chin, Michael S. Brown, David Suter

We investigate projective estimation under model inadequacies, i. e., when the underpinning assumptions of the projective model are not fully satisfied by the data.

Image Stitching

Cannot find the paper you are looking for? You can Submit a new open access paper.