Results 41 to 50 of about 26,254 (190)
RA-Depth: Resolution Adaptive Self-supervised Monocular Depth Estimation
, 2022 Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe performance degradation when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions.
He, Mu +5 more
openaire +2 more sources
Depth-Relative Self Attention for Monocular Depth Estimation
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023 Monocular depth estimation is very challenging because clues to the exact depth are incomplete in a single RGB image. To overcome the limitation, deep neural networks rely on various visual hints such as size, shade, and texture extracted from RGB information. However, we observe that if such hints are overly exploited, the network can be biased on RGB
Shim, Kyuhong +3 more
openaire +2 more sources
Learning Depth for Scene Reconstruction Using an Encoder-Decoder Model
IEEE Access, 2020 Depth estimation has received considerable attention and is often applied to visual simultaneous localization and mapping (SLAM) for scene reconstruction.
Xiaohan Tu +6 more
doaj +1 more source
Monocular Depth Estimation Based on Multi-Scale Depth Map Fusion
IEEE Access, 2021 Monocular depth estimation is a basic task in machine vision. In recent years, the performance of monocular depth estimation has been greatly improved. However, most depth estimation networks are based on a very deep network to extract features that lead
Xin Yang +4 more
doaj +1 more source
DeepFusion encoder for unsupervised monocular metric depth estimation [PDF]
PeerJ Computer ScienceMonocular depth estimation is a fundamental task in computer vision, with significant applications in autonomous driving and robotics. However, accurately estimating depth from a single image remains challenging due to the absence of direct depth cues ...
Zhiwei Huang +6 more
doaj +2 more sources
Geometry meets semantics for semi-supervised monocular depth estimation
, 2018 Depth estimation from a single image represents a very exciting challenge in computer vision. While other image-based depth sensing techniques leverage on the geometry between different viewpoints (e.g., stereo or structure from motion), the lack of ...
A Geiger +9 more
core +1 more source
Gradient-Based Uncertainty for Monocular Depth Estimation
, 2022 In monocular depth estimation, disturbances in the image context, like moving objects or reflecting materials, can easily lead to erroneous predictions. For that reason, uncertainty estimates for each pixel are necessary, in particular for safety-critical applications such as automated driving.
Hornauer, Julia, Belagiannis, Vasileios
openaire +2 more sources
FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation
2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 Accepted by ...
Zhu, Junyu +5 more
openaire +2 more sources
Unsupervised Learning of Depth and Ego-Motion from Video
, 2017 We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. We achieve this by simultaneously training depth and camera pose estimation networks using the task of view ...
Brown, Matthew +3 more
core +1 more source
Aperture Supervision for Monocular Depth Estimation
, 2018 We present a novel method to train machine learning algorithms to estimate scene depths from a single image, by using the information provided by a camera's aperture as supervision.
Barron, Jonathan T. +4 more
core +1 more source