Search Results for author:
Found 48 papers, 23 papers with code
GamutMLP: A Lightweight MLP for Color Loss Recovery
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.
MIMT: Multi-Illuminant Color Constancy via Multi-Task Learning
Moreover, to ensure that our model maintains the constancy of surface colors regardless of the variations of light colors, we also preserve local surface color features in our model.
Day-to-Night Image Synthesis for Training Nighttime Neural ISPs
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.
Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata
Our experiments show that our learned sampling can adapt to the image content to produce better raw reconstructions than existing methods.
Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images
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.
Modeling sRGB Camera Noise with Normalizing Flows
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.
Multi-View Motion Synthesis via Applying Rotated Dual-Pixel Blur Kernels
In this work, we follow the trend of rendering the NIMAT effect by introducing a modification on the blur synthesis procedure in portrait mode.
Auto White-Balance Correction for Mixed-Illuminant Scenes
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
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.
Neural Image Representations for Multi-Image Fusion and Layer Separation
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.
CAMS: Color-Aware Multi-Style Transfer
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.
Leveraging the Availability of Two Cameras for Illuminant Estimation
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.
Mobile Computational Photography: A Tour
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.
Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data
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 #12 on
Image Defocus Deblurring
on DPD (Dual-view)
(using extra training data)
HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms
This goal has led to significant interest in methods that can intuitively control the appearance of images generated by GANs.
AIM 2020: Scene Relighting and Illumination Estimation Challenge
The first track considered one-to-one relighting; the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation (i. e., light source position).
Interactive White Balancing for Camera-Rendered Images
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.
CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks
Because of this, a number of methods have been proposed to "unprocess" nonlinear images back to a raw-RGB state.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
A Little Bit More: Bitplane-Wise Bit-Depth Recovery
Imaging sensors digitize incoming scene light at a dynamic range of 10--12 bits (i. e., 1024--4096 tonal values).
Defocus Deblurring Using Dual-Pixel Data
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.
Ranked #6 on
Image Defocus Deblurring
on DPD
Deep White-Balance Editing
The ISP rendering begins with a white-balance procedure that is used to remove the color cast of the scene's illumination.
Learning Multi-Scale Photo Exposure Correction
In contrast, our proposed method targets both over- and underexposure errors in photographs.
Ranked #3 on
Image Enhancement
on Exposure-Errors
What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance
There is active research targeting local image manipulations that can fool deep neural networks (DNNs) into producing incorrect results.
Sensor-Independent Illumination Estimation for DNN Models
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.
Noise Flow: Noise Modeling with Conditional Normalizing Flows
Modeling and synthesizing image noise is an important aspect in many computer vision applications.
As-projective-as-possible bias correction for illumination estimation algorithms
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
The fact that different objectives exist raises the research question of whether there is a preferred objective.
Classification-Driven Dynamic Image Enhancement
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.
Improving Color Reproduction Accuracy on Cameras
In this paper, we discuss the limitations of the current colorimetric mapping approach and propose two methods that are able to improve color accuracy.
A High-Quality Denoising Dataset for Smartphone Cameras
We propose a systematic procedure for estimating ground truth for noisy images that can be used to benchmark denoising performance for smartphone cameras.
Classification Driven Dynamic Image Enhancement
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.
Why You Should Forget Luminance Conversion and Do Something Better
One of the most frequently applied low-level operations in computer vision is the conversion of an RGB camera image into its luminance representation.
A Non-Local Low-Rank Framework for Ultrasound Speckle Reduction
`Speckle' refers to the granular patterns that occur in ultrasound images due to wave interference.
Haze Visibility Enhancement: A Survey and Quantitative Benchmarking
This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes.
Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras
In particular, due to the differences in spectral sensitivities of the cameras, different cameras yield different RGB measurements for the same spectral signal.
Rain Streak Removal Using Layer Priors
This paper addresses the problem of rain streak removal from a single image.
RAW Image Reconstruction Using a Self-Contained sRGB-JPEG Image With Only 64 KB Overhead
Most camera images are saved as 8-bit standard RGB (sRGB) compressed JPEGs.
Two Illuminant Estimation and User Correction Preference
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.
Nighttime Haze Removal With Glow and Multiple Light Colors
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.
SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs
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.
Beyond White: Ground Truth Colors for Color Constancy Correction
A limitation in color constancy research is the inability to establish ground truth colors for evaluating corrected images.
Fast and Effective L0 Gradient Minimization by Region Fusion
L_0 gradient minimization can be applied to an input signal to control the number of non-zero gradients.
Effective Learning-Based Illuminant Estimation Using Simple Features
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.
Illuminant Aware Gamut-Based Color Transfer
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.
Single Image Layer Separation using Relative Smoothness
This problem arises most notably in intrinsic image decomposition and reflection interference removal.
Raw-to-Raw: Mapping between Image Sensor Color Responses
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
We investigate projective estimation under model inadequacies, i. e., when the underpinning assumptions of the projective model are not fully satisfied by the data.
