Therefore, in order to improve the perception and decision-making ability of autonomous robot systems, Simultaneous localization and mapping (SLAM) and autonomous trajectory planning are widely researched, especially combining learning-based algorithms.
This paper introduces a divide-and-conquer inspired adversarial learning (DACAL) approach for photo enhancement.
While Deep Neural Networks (DNNs) trained for image and video super-resolution regularly achieve new state-of-the-art performance, they also suffer from significant drawbacks.
We treat the problem of color enhancement as an image translation task, which we tackle using both supervised and unsupervised learning.
This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs.
Here we present a novel framework to solve such problems with deep learning by casting the original problem as a continuum of intermediate representations between the input and output data.
In practical verification, we design a new regularization structure with guided feature to produce GNN-based filtering and propagation diffusion to tackle the ill-posed inverse problems of quotient image analysis (QIA), which recovers the reflectance ratio as a signature for image analysis or adjustment.
Contrast enhancement and noise removal are coupled problems for low-light image enhancement.
To our best knowledge, we are the first one to explore residual and illumination for shadow removal.
Additionally, a weighting scheme in the loss computation that favors high-frequency structures is proposed to focus on the important details and contours in projection imaging.