AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection

Y Wang, T Xu, F Zhang, T Xue, J Gu - arXiv preprint arXiv:2410.22939, 2024 - arxiv.org
Image Signal Processors (ISPs) convert raw sensor signals into digital images, which
significantly influence the image quality and the performance of downstream computer …

Software-Defined Imaging: A Survey

S Jayasuriya, O Iqbal, V Kodukula… - Proceedings of the …, 2023 - ieeexplore.ieee.org
Huge advancements have been made over the years in terms of modern image-sensing
hardware and visual computing algorithms (eg, computer vision, image processing, and …

Logarithmic Lenses: Exploring Log RGB Data for Image Classification

BA Maxwell, S Singhania, A Patel… - Proceedings of the …, 2024 - openaccess.thecvf.com
The design of deep network architectures and training methods in computer vision has been
well-explored. However in almost all cases the images have been used as provided with …

Guiding a Harsh-Environments Robust Detector via RAW Data Characteristic Mining

H Chen, HS Tai, K Ma - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
Consumer-grade cameras capture the RAW physical description of a scene and then
process the image signals to obtain high-quality RGB images that are faithful to human …

PAIR: Perception Aided Image Restoration for Natural Driving Conditions

P Shyam, HJ Yoo - Proceedings of the IEEE/CVF Winter …, 2024 - openaccess.thecvf.com
We present a two-stage mechanism for generic image restoration in natural driving
conditions, where multiple non-linear degradations simultaneously impact perception for …

Enhanced object detection by integrating camera parameters into raw image-based faster r-cnn

C Wei, G Wu, M Barth, PH Chan… - 2023 IEEE 26th …, 2023 - ieeexplore.ieee.org
The rapid progress in intelligent vehicle technology has led to a significant reliance on
computer vision and deep neural networks (DNNs) to improve road safety and driving …

Raw instinct: Trust your classifiers and skip the conversion

C Kantas, B Antoniussen, MV Andersen… - 2023 IEEE 6th …, 2023 - ieeexplore.ieee.org
Using RAW-images in computer vision problems is surprisingly underexplored considering
that converting from RAW to RGB does not introduce any new capture information. In this …

Generalizing ISP Model by Unsupervised Raw-to-raw Mapping

D Xie, C Qiao, L Liang, Z Wang, T Li, Q Liu… - Proceedings of the …, 2024 - dl.acm.org
ISP (Image Signal Processor) serves as a pipeline converting unprocessed raw images to
sRGB images, positioned before nearly all visual tasks. Due to the varying spectral …

Leveraging Content and Context Cues for Low-Light Image Enhancement

I Morawski, K He, S Dangi, WH Hsu - arXiv preprint arXiv:2412.07693, 2024 - arxiv.org
Low-light conditions have an adverse impact on machine cognition, limiting the performance
of computer vision systems in real life. Since low-light data is limited and difficult to annotate …

RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation

C Reinders, R Berdan, B Besbinar, J Otsuka… - arXiv preprint arXiv …, 2024 - arxiv.org
Current deep learning approaches in computer vision primarily focus on RGB data
sacrificing information. In contrast, RAW images offer richer representation, which is crucial …