Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild

We propose a trainable Image Signal Processing (ISP) framework that produces DSLR quality images given RAW images captured by a smartphone. To address the color misalignments between training image pairs, we employ a color-conditional ISP network and optimize a novel parametric color mapping between each input RAW and reference DSLR image. During inference, we predict the target color image by designing a color prediction network with efficient Global Context Transformer modules. The latter effectively leverage global information to learn consistent color and tone mappings. We further propose a robust masked aligned loss to identify and discard regions with inaccurate motion estimation during training. Lastly, we introduce the ISP in the Wild (ISPW) dataset, consisting of weakly paired phone RAW and DSLR sRGB images. We extensively evaluate our method, setting a new state-of-the-art on two datasets.

READ FULL TEXT

page 27

page 28

page 29

page 30

page 31

page 32

page 33

page 34

research
08/18/2021

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision

Learning RAW-to-sRGB mapping has drawn increasing attention in recent ye...
research
03/20/2022

CRISPnet: Color Rendition ISP Net

Image signal processors (ISPs) are historically grown legacy software sy...
research
08/20/2020

AWNet: Attentive Wavelet Network for Image ISP

As the revolutionary improvement being made on the performance of smartp...
research
06/25/2021

Semi-Supervised Raw-to-Raw Mapping

The raw-RGB colors of a camera sensor vary due to the spectral sensitivi...
research
03/17/2017

Smartphone Based Colorimetric Detection via Machine Learning

We report the application of machine learning to smartphone based colori...
research
05/17/2022

Towards Robust Low Light Image Enhancement

In this paper, we study the problem of making brighter images from dark ...
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...

Please sign up or login with your details

Forgot password? Click here to reset