Augundo: Scaling up augmentations for monocular depth completion and estimation

Y Wu, TY Liu, H Park, S Soatto, D Lao… - European Conference on …, 2024 - Springer
Unsupervised depth completion and estimation methods are trained by minimizing
reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are …

Uncle: Unsupervised continual learning of depth completion

S Gangopadhyay, X Chen, M Chu, P Rim… - arxiv preprint arxiv …, 2024 - arxiv.org
We propose UnCLe, a standardized benchmark for Unsupervised Continual Learning of a
multimodal depth estimation task: Depth completion aims to infer a dense depth map from a …

A simple yet universal framework for depth completion

JH Park, HG Jeon - The Thirty-eighth Annual Conference on Neural …, 2024 - openreview.net
Consistent depth estimation across diverse scenes and sensors is a crucial challenge in
computer vision, especially when deploying machine learning models in the real world …