Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training

arXiv:2403.14089v1 Announce Type: new
Abstract: Unsupervised intrinsic image decomposition (IID) is the process of separating a natural image into albedo and shade without these ground truths. A recent model employing light detection and ranging (LiDAR) intensity demonstrated impressive performance, though the necessity of LiDAR intensity during inference restricts its practicality. Thus, IID models employing only a single image during inference while keeping as high IID quality as the one with an image plus LiDAR intensity are highly desired. To address …

abstract arxiv cs.cv detection image inference intensity intrinsic lidar light natural performance process training type unsupervised