TY - JOUR AU - Chung, Audrey G. AU - Wong, Alexander PY - 2016/10/03 Y2 - 2024/03/28 TI - Noise Suppression and Contrast Enhancement via Bayesian Residual Transform (BRT) in Low-Light Conditions JF - Journal of Computational Vision and Imaging Systems JA - J. Comp. Vis. Imag. Sys. VL - 2 IS - 1 SE - Articles DO - 10.15353/vsnl.v2i1.110 UR - https://openjournals.uwaterloo.ca/index.php/vsl/article/view/110 SP - AB - <p>Very low-light conditions are problematic for current robotic vision<br />algorithms as captured images are subject to high levels of ISO<br />noise. We propose a Bayesian Residual Transform (BRT) model for<br />joint noise suppression and image enhancement for images captured<br />under these low-light conditions via a Bayesian-based multiscale<br />image decomposition. The BRT models a given image as the<br />sum of residual images, and the denoised image is reconstructed<br />using a weighted summation of these residual images. We evaluate<br />the efficacy of the proposed BRT model using the VIP-LowLight<br />dataset, and preliminary results show a notable visual improvement<br />over state-of-the-art denoising methods.</p> ER -