Learning to See in the Dark

Chen, Chen; Chen, Qifeng; Xu, Jia; Koltun, Vladlen

doi:10.1109/cvpr.2018.00347

Cited by 1,130 publications

(899 citation statements)

References 31 publications

Supporting

Mentioning

856

Contrasting

Unclassified

Order By: Relevance

“…evaluation script from authors' project page 3 . In both cases, whitened descriptors were used for comparison.…”

Section: Compared Methodsmentioning

confidence: 99%

“…Methods enhancing visual quality of images taken under bad light conditions were proposed. In [3], raw output from the image sensor is taken and a neural network is used to enhance the visual appearance, as if the image was taken with long exposure. Camera (sensor) dependent models are learned from a dataset of multiple-exposure images of static scenes with qualitatively very impressive results.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

No Fear of the Dark: Image Retrieval Under Varying Illumination Conditions

Jenícek

Chum

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Image retrieval under varying illumination conditions, such as day and night images, is addressed by image preprocessing, both hand-crafted and learned. Prior to extracting image descriptors by a convolutional neural network, images are photometrically normalised in order to reduce the descriptor sensitivity to illumination changes. We propose a learnable normalisation based on the U-Net architecture, which is trained on a combination of single-camera multiexposure images and a newly constructed collection of similar views of landmarks during day and night. We experimentally show that both hand-crafted normalisation based on local histogram equalisation and the learnable normalisation outperform standard approaches in varying illumination conditions, while staying on par with the state-ofthe-art methods on daylight illumination benchmarks, such as Oxford or Paris datasets.

show abstract

“…evaluation script from authors' project page 3 . In both cases, whitened descriptors were used for comparison.…”

Section: Compared Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

No Fear of the Dark: Image Retrieval Under Varying Illumination Conditions

Jenícek

Chum

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…In recent work, the use of deep convolutional neural networks (CNNs) has become a common theme to improve image processing algorithms for a better imaging pipeline. Examples include models that perform demosaicing [4], denoising [5,6], and many other types of image enhancement and transformation methods [7,8,9].…”

Section: Related Workmentioning

confidence: 99%

VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications

Isikdogan

Sushma

et al. 2019

2019 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications. We propose a set of methods, which we collectively call VisionISP, to repurpose the ISP for machine consumption. VisionISP significantly reduces data transmission needs by reducing the bit-depth and resolution while preserving the relevant information. The blocks in VisionISP are simple, content-aware, and trainable. Experimental results show that VisionISP boosts the performance of a subsequent computer vision system trained to detect objects in an autonomous driving setting. The results demonstrate the potential and the practicality of VisionISP for computer vision applications.

show abstract

“…For the final 8 epoch, we use 224*224 pixels image patches with constant learning-rate. To fully utilize the GPU memory, the batch size is also decreasing as [16,4,2,2] on a single NVIDIA TitanX GPU. We use the random crop on full-resolution image patches instead of interpolation when changing resolution.…”

Section: Training Detailsmentioning

confidence: 99%

HighEr-Resolution Network for Image Demosaicing and Enhancing

Mei

Zhang³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Neural-networks based image restoration methods tend to use low-resolution image patches for training. Although higher-resolution image patches can provide more global information, state-of-the-art methods cannot utilize them due to their huge GPU memory usage, as well as the instable training process. However, plenty of studies have shown that global information is crucial for image restoration tasks like image demosaicing and enhancing. In this work, we propose a HighEr-Resolution Network (HERN) to fully learning global information in high-resolution image patches. To achieve this, the HERN employs two parallel paths to learn image features in two different resolution, respectively. By combining global-aware features and multi-scale features, our HERN is able to learn global information with feasible GPU memory usage. Besides, we introduce a progressive training method to solve the instability issue and accelerate model convergence. On the task of image demosaicing and enhancing, our HERN achieves state-of-the-art performance on the AIM2019 RAW to RGB mapping challenge. The source code of our implementation is available at https://github.com/MKFMIKU/ RAW2RGBNet.

show abstract

Learning to See in the Dark

Cited by 1,130 publications

References 31 publications

No Fear of the Dark: Image Retrieval Under Varying Illumination Conditions

No Fear of the Dark: Image Retrieval Under Varying Illumination Conditions

VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications

HighEr-Resolution Network for Image Demosaicing and Enhancing

Contact Info

Product

Resources

About