Bilateral guided radiance field processing

Y Wang, C Wang, B Gong, T Xue - ACM Transactions on Graphics (TOG), 2024 - dl.acm.org
Neural Radiance Fields (NeRF) achieves unprecedented performance in synthesizing novel
view synthesis, utilizing multi-view consistency. When capturing multiple inputs, image …

Raw image reconstruction with learned compact metadata

Y Wang, Y Yu, W Yang, L Guo… - Proceedings of the …, 2023 - openaccess.thecvf.com
While raw images exhibit advantages over sRGB images (eg linearity and fine-grained
quantization level), they are not widely used by common users due to the large storage …

Beyond the pixel: a photometrically calibrated HDR dataset for luminance and color prediction

C Bolduc, J Giroux, M Hébert… - Proceedings of the …, 2023 - openaccess.thecvf.com
Light plays an important role in human well-being. However, most computer vision tasks
treat pixels without considering their relationship to physical luminance. To address this …

Metadata-based raw reconstruction via implicit neural functions

L Li, H Qiao, Q Ye, Q Yang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Many low-level computer vision tasks are desirable to utilize the unprocessed RAW image
as input, which remains the linear relationship between pixel values and scene radiance …

Reversed image signal processing and RAW reconstruction. AIM 2022 challenge report

MV Conde, R Timofte, Y Huang, J Peng… - … on Computer Vision, 2022 - Springer
Cameras capture sensor RAW images and transform them into pleasant RGB images,
suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous …

Leveraging frame affinity for srgb-to-raw video de-rendering

C Zhang, W Han, Y Zhou, J Shen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Unprocessed RAW video has shown distinct advantages over sRGB video in video editing
and computer vision tasks. However capturing RAW video is challenging due to limitations …

An overview of bit-depth enhancement: Algorithm datasets and evaluation

J Liu, X Li, G Zhai - Displays, 2024 - Elsevier
To enhance the visualization of images on high dynamic range (HDR) monitors, it is
essential to employ bit-depth enhancement (BDE) methods for converting low bit-depth …

Paramisp: learned forward and inverse ISPS using camera parameters

W Kim, G Kim, J Lee, S Lee, SH Baek, S Cho - ar**_Computer_Graphics_Images_to_Sensor_RAW_Images_ICCV_2023_paper.pdf" data-clk="hl=uk&sa=T&oi=gga&ct=gga&cd=8&d=9076648202456117751&ei=TE2-Z4nSNI-w6rQPpeb7oAg" data-clk-atid="97GVMnO79n0J" target="_blank">[PDF] thecvf.com

Graphics2RAW: map** computer graphics images to sensor raw images

D Seo, A Punnappurath, L Zhao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Computer graphics (CG) rendering platforms produce imagery with ever-increasing photo
realism. The narrowing domain gap between real and synthetic imagery makes it possible to …

Beyond learned metadata-based raw image reconstruction

Y Wang, Y Yu, W Yang, L Guo, LP Chau, AC Kot… - International Journal of …, 2024 - Springer
While raw images possess distinct advantages over sRGB images, eg, linearity and fine-
grained quantization levels, they are not widely adopted by general users due to their …