On the pitfalls of heteroscedastic uncertainty estimation with probabilistic neural networks

M Seitzer, A Tavakoli, D Antic, G Martius - arxiv preprint arxiv:2203.09168, 2022 - arxiv.org
Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep
learning, a common approach to this end is to train a neural network to estimate the …

Diffcad: Weakly-supervised probabilistic cad model retrieval and alignment from an rgb image

D Gao, D Rozenberszki, S Leutenegger… - ACM Transactions on …, 2024 - dl.acm.org
Perceiving 3D structures from RGB images based on CAD model primitives can enable an
effective, efficient 3D object-based representation of scenes. However, current approaches …

High-resolution depth estimation for 360deg panoramas through perspective and panoramic depth images registration

CH Peng, J Zhang - Proceedings of the IEEE/CVF Winter …, 2023 - openaccess.thecvf.com
We propose a novel approach to compute high-resolution (2048x1024 and higher) depths
for panoramas that is significantly faster and qualitatively and qualitatively more accurate …

Monovan: Visual attention for self-supervised monocular depth estimation

I Indyk, I Makarov - … on Mixed and Augmented Reality (ISMAR), 2023 - ieeexplore.ieee.org
Depth estimation is crucial in various computer vision applications, including autonomous
driving, robotics, and virtual and augmented reality. An accurate scene depth map is …

Out-of-Distribution Detection for Monocular Depth Estimation

J Hornauer, A Holzbock… - Proceedings of the …, 2023 - openaccess.thecvf.com
In monocular depth estimation, uncertainty estimation approaches mainly target the data
uncertainty introduced by image noise. In contrast to prior work, we address the uncertainty …

MobileDepth: Monocular depth estimation based on lightweight vision transformer

Y Li, X Wei - Applied Artificial Intelligence, 2024 - Taylor & Francis
As deep learning takes off, monocular depth estimation based on convolutional neural
networks (CNNs) has made impressive progress. CNNs are superior at extracting local …

AMENet is a monocular depth estimation network designed for automatic stereoscopic display

T Wu, Z **a, M Zhou, LB Kong, Z Chen - Scientific Reports, 2024 - nature.com
Monocular depth estimation has a wide range of applications in the field of autostereoscopic
displays, while accuracy and robustness in complex scenes are still a challenge. In this …

Learning from the Giants: A Practical Approach to Underwater Depth and Surface Normals Estimation

A Saleh, M Olsen, B Senadji, MR Azghadi - arxiv preprint arxiv …, 2024 - arxiv.org
Monocular Depth and Surface Normals Estimation (MDSNE) is crucial for tasks such as 3D
reconstruction, autonomous navigation, and underwater exploration. Current methods rely …

3D Hand Mesh Recovery from Monocular RGB in Camera Space

H Li, PPK Chen, Y Zhou - arxiv preprint arxiv:2405.07167, 2024 - arxiv.org
With the rapid advancement of technologies such as virtual reality, augmented reality, and
gesture control, users expect interactions with computer interfaces to be more natural and …

High-Resolution Depth Estimation for 360-degree Panoramas through Perspective and Panoramic Depth Images Registration

CH Peng, J Zhang - arxiv preprint arxiv:2210.10414, 2022 - arxiv.org
We propose a novel approach to compute high-resolution (2048x1024 and higher) depths
for panoramas that is significantly faster and qualitatively and qualitatively more accurate …