Overexposure Mask Fusion: Generalizable Reverse ISP Multi-Step Refinement

10/20/2022
by   Jinha Kim, et al.
0

With the advent of deep learning methods replacing the ISP in transforming sensor RAW readings into RGB images, numerous methodologies solidified into real-life applications. Equally potent is the task of inverting this process which will have applications in enhancing computational photography tasks that are conducted in the RAW domain, addressing lack of available RAW data while reaping from the benefits of performing tasks directly on sensor readings. This paper's proposed methodology is a state-of-the-art solution to the task of RAW reconstruction, and the multi-step refinement process integrating an overexposure mask is novel in three ways: instead of from RGB to bayer, the pipeline trains from RGB to demosaiced RAW allowing use of perceptual loss functions; the multi-step processes has greatly enhanced the performance of the baseline U-Net from start to end; the pipeline is a generalizable process of refinement that can enhance other high performance methodologies that support end-to-end learning.

READ FULL TEXT

page 10

page 11

page 12

page 13

research
04/07/2021

PyNET-CA: Enhanced PyNET with Channel Attention for End-to-End Mobile Image Signal Processing

Reconstructing RGB image from RAW data obtained with a mobile device is ...
research
06/03/2022

Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata

Most camera images are rendered and saved in the standard RGB (sRGB) for...
research
06/23/2020

CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks

Cameras currently allow access to two image states: (i) a minimally proc...
research
01/10/2022

Model-Based Image Signal Processors via Learnable Dictionaries

Digital cameras transform sensor RAW readings into RGB images by means o...
research
10/17/2022

Reversing Image Signal Processors by Reverse Style Transferring

RAW image datasets are more suitable than the standard RGB image dataset...
research
11/20/2019

W-Net: Two-stage U-Net with misaligned data for raw-to-RGB mapping

Recent research on a learning mapping between raw Bayer images and RGB i...
research
10/21/2020

How Can Businesses Best Leverage Data scrubbing?

The hype around data is hardly news. It is a critical part of a business...

Please sign up or login with your details

Forgot password? Click here to reset