GenISP: Neural ISP for Low-Light Machine Cognition

• URL: http://arxiv.org/abs/2205.03688v1
• Date: Sat, 7 May 2022 17:17:24 GMT
• Title: GenISP: Neural ISP for Low-Light Machine Cognition
• Authors: Igor Morawski and Yu-An Chen and Yu-Sheng Lin and Shusil Dangi and Kai He and Winston H. Hsu
• Abstract summary: In low-light conditions, object detectors using raw image data are more robust than detectors using image data processed by an ISP pipeline. We propose a minimal neural ISP pipeline for machine cognition, named GenISP, that explicitly incorporates Color Space Transformation to a device-independent color space.
• Score: 19.444297600977546
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Object detection in low-light conditions remains a challenging but important problem with many practical implications. Some recent works show that, in low-light conditions, object detectors using raw image data are more robust than detectors using image data processed by a traditional ISP pipeline. To improve detection performance in low-light conditions, one can fine-tune the detector to use raw image data or use a dedicated low-light neural pipeline trained with paired low- and normal-light data to restore and enhance the image. However, different camera sensors have different spectral sensitivity and learning-based models using raw images process data in the sensor-specific color space. Thus, once trained, they do not guarantee generalization to other camera sensors. We propose to improve generalization to unseen camera sensors by implementing a minimal neural ISP pipeline for machine cognition, named GenISP, that explicitly incorporates Color Space Transformation to a device-independent color space. We also propose a two-stage color processing implemented by two image-to-parameter modules that take down-sized image as input and regress global color correction parameters. Moreover, we propose to train our proposed GenISP under the guidance of a pre-trained object detector and avoid making assumptions about perceptual quality of the image, but rather optimize the image representation for machine cognition. At the inference stage, GenISP can be paired with any object detector. We perform extensive experiments to compare our method to other low-light image restoration and enhancement methods in an extrinsic task-based evaluation and validate that GenISP can generalize to unseen sensors and object detectors. Finally, we contribute a low-light dataset of 7K raw images annotated with 46K bounding boxes for task-based benchmarking of future low-light image restoration and object detection.

Related papers

• Simple Image Signal Processing using Global Context Guidance [56.41827271721955]
  Deep learning-based ISPs aim to transform RAW images into DSLR-like RGB images using deep neural networks. We propose a novel module that can be integrated into any neural ISP to capture the global context information from the full RAW images. Our model achieves state-of-the-art results on different benchmarks using diverse and real smartphone images.
  arXiv  Detail & Related papers  (2024-04-17T17:11:47Z)
• You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement [50.37253008333166]
  Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images. We propose a novel trainable color space, named Horizontal/Vertical-Intensity (HVI) It not only decouples brightness and color from RGB channels to mitigate the instability during enhancement but also adapts to low-light images in different illumination ranges due to the trainable parameters.
  arXiv  Detail & Related papers  (2024-02-08T16:47:43Z)
• Enhancing Low-Light Images Using Infrared-Encoded Images [81.8710581927427]
  Previous arts mainly focus on the low-light images captured in the visible spectrum using pixel-wise loss. We propose a novel approach to increase the visibility of images captured under low-light environments by removing the in-camera infrared (IR) cut-off filter.
  arXiv  Detail & Related papers  (2023-07-09T08:29:19Z)
• Polarimetric Imaging for Perception [3.093890460224435]
  We analyze the potential for improvement in perception tasks when using an RGB-polarimetric camera. We show that a quantifiable improvement can be achieved for both of them using state-of-the-art deep neural networks.
  arXiv  Detail & Related papers  (2023-05-24T06:42:27Z)
• Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method [51.30748775681917]
  We consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method.
  arXiv  Detail & Related papers  (2022-12-22T09:05:07Z)
• Enabling ISP-less Low-Power Computer Vision [4.102254385058941]
  We release the raw version of a large-scale benchmark for generic high-level vision tasks. For ISP-less CV systems, training on raw images result in a 7.1% increase in test accuracy. We propose an energy-efficient form of analog in-pixel demosaicing that may be coupled with in-pixel CNN computations.
  arXiv  Detail & Related papers  (2022-10-11T13:47:30Z)
• Learning Enriched Illuminants for Cross and Single Sensor Color Constancy [182.4997117953705]
  We propose cross-sensor self-supervised training to train the network. We train the network by randomly sampling the artificial illuminants in a sensor-independent manner. Experiments show that our cross-sensor model and single-sensor model outperform other state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2022-03-21T15:45:35Z)
• Model-Based Image Signal Processors via Learnable Dictionaries [6.766416093990318]
  Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP) Recent approaches have attempted to bridge this gap by estimating the RGB to RAW mapping. We present a novel hybrid model-based and data-driven ISP that is both learnable and interpretable.
  arXiv  Detail & Related papers  (2022-01-10T08:36:10Z)
• Thermal Image Processing via Physics-Inspired Deep Networks [21.094006629684376]
  DeepIR combines physically accurate sensor modeling with deep network-based image representation. DeepIR requires neither training data nor periodic ground-truth calibration with a known black body target. Simulated and real data experiments demonstrate that DeepIR can perform high-quality non-uniformity correction with as few as three images.
  arXiv  Detail & Related papers  (2021-08-18T04:57:48Z)
• Learning Camera Miscalibration Detection [83.38916296044394]
  This paper focuses on a data-driven approach to learn the detection of miscalibration in vision sensors, specifically RGB cameras. Our contributions include a proposed miscalibration metric for RGB cameras and a novel semi-synthetic dataset generation pipeline based on this metric. By training a deep convolutional neural network, we demonstrate the effectiveness of our pipeline to identify whether a recalibration of the camera's intrinsic parameters is required or not.
  arXiv  Detail & Related papers  (2020-05-24T10:32:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.