Non-local color compensation network for intrinsic image decomposition

F Zhang, X Jiang, Z Xia, M Gabbouj… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Single image-based intrinsic image decomposition attempts to separate one input image
into several intrinsic components, which is inherently an under-constrained problem. Some …

Intrinsic Appearance Decomposition Using Point Cloud Representation

X Xing, K Groh, S Karaoglu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The aim of intrinsic decomposition is to deduce the albedo and shading components,
typically from 2D images. However, this task is ill-posed, necessitating previous methods to …

Intrinsic omnidirectional image decomposition with illumination pre-extraction

RK Xu, L Zhang, FL Zhang - IEEE Transactions on Visualization …, 2024 - ieeexplore.ieee.org
Capturing an omnidirectional image with a 360-degree field of view entails capturing
intricate spatial and lighting details of the scene. Consequently, existing intrinsic image …

Extraordinarily Time-and Memory-Efficient Large-Scale Canonical Correlation Analysis in Fourier Domain: From Shallow to Deep

XJ Shen, Z Xu, L Wang, Z Li, G Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Canonical correlation analysis (CCA) is a correlation analysis technique that is widely used
in statistics and the machine-learning community. However, the high complexity involved in …

CRefNet: Learning Consistent Reflectance Estimation With a Decoder-Sharing Transformer

J Luo, N Zhao, W Li, C Richardt - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
We present CRefNet, a hybrid transformer-convolutional deep neural network for consistent
reflectance estimation in intrinsic image decomposition. Estimating consistent reflectance is …

Intrinsic Image Decomposition Based on Retinex Theory, Superpixel Segmentation and Scale-Space Computations

D Ulucan, O Ulucan, M Ebner - International Workshop on Computational …, 2024 - Springer
Intrinsic image decomposition enables us to estimate the low-level features of images. Due
to the benefits it provides and the challenges it holds, intrinsic image decomposition has …

Time and Memory Efficient Large-Scale Canonical Correlation Analysis in Fourier Domain

XJ Shen, Z Xu, L Wang, Z Li - Proceedings of the 30th ACM International …, 2022 - dl.acm.org
Canonical correlation analysis (CCA) is a linear correlation analysis technique used widely
in the statistics and machine learning community. However, the high complexity involved in …

Single Scene Image Editing Based on Deep Intrinsic Decomposition

H Sha, Y Liu, K Lu, C Lu, H Chen, Y Wang - Image and Graphics: 11th …, 2021 - Springer
Intrinsic decomposition is an inherent problem in computer graphics and computer vision,
which decomposes an image into a reflectance image and a shading image. Through the …