Results 121 to 130 of about 1,194,643 (283)

Image depth estimation assisted by multi-view projection

Complex & Intelligent Systems
In recent years, deep learning has significantly advanced the development of image depth estimation algorithms. The depth estimation network with single-view input can only extract features from a single 2D image, often neglecting the information ...
Liman Liu, Jinshan Tian, Guansheng Luo, Siyuan Xu, Chen Zhang, Huaifei Hu, Wenbing Tao   +6 more
doaj   +1 more source

Mono-ViM: A Self-Supervised Mamba Framework for Monocular Depth Estimation in Endoscopic Scenes

Mathematics
Self-supervised depth estimation methods enable the recovery of scene depth information from monocular endoscopic images, thereby assisting endoscopic navigation.
Shengli Chen, Yuming Chen, Xiaoang Xu, Jiahao Li, Ke Ye, Tianzuo Chang   +5 more
doaj   +1 more source

Amodal Depth Anything: Amodal Depth Estimation in the Wild

CoRR
Amodal depth estimation aims to predict the depth of occluded (invisible) parts of objects in a scene. This task addresses the question of whether models can effectively perceive the geometry of occluded regions based on visible cues. Prior methods primarily rely on synthetic datasets and focus on metric depth estimation, limiting their generalization ...
Zhenyu Li 0007, Mykola Lavreniuk, Jian Shi, Shariq Farooq Bhat, Peter Wonka   +4 more
openaire   +2 more sources

Interactions between Molten High‐Silicon Electrical Steels and Carbon‐Bonded MgO Refractories Based on Recyclates

Advanced Engineering Materials, EarlyView.
This study examines how several molten high‐silicon electrical steels interact with both conventional and recycled MgO–C refractories. For this, various immersion experiments are conducted. In addition to infiltration, a number of mechanisms are identified and explained that control the corrosion of the refractory material.
Lukas Neubert, Matheus Roberto Bellé, Anton Yehorov, Anhelina Mospan, Till M. J. Stadtmüller, Seetharaman Sridhar, Christos G. Aneziris, Olena Volkova   +7 more
wiley   +1 more source

Prediction of Surface Topography Parameters in Direct Laser Interference Patterning of Stainless Steel Using Infrared Monitoring and Convolutional Neural Networks

Advanced Engineering Materials, EarlyView.
This study presents an infrared monitoring approach for direct laser interference patterning (DLIP) combined with a convolutional neural network (CNN). Thermal emission data captured during structuring are used to predict surface topography parameters.
Lukas Olawsky, Marcelo Sallese, Leander Kläber, Clemens Kuhn, Keming Du, Andrés Fabián Lasagni   +5 more
wiley   +1 more source

AURA-Depth: Attention-Based Uncertainty Reduction and Feature Aggregation Depth Network

IEEE Access
Reliable depth information is crucial in autonomous driving technology. However, monocular depth estimation often faces inherent limitations such as scale ambiguity and lack of depth cues.
Youngtak Na, Sungho Woo, Soonyoung Lee, Byung Jun Kang   +3 more
doaj   +1 more source

Interaction between Molten Al‐Killed Mn–B Steel and Carbon‐Bonded MgO Refractories Based on Recyclates

Advanced Engineering Materials, EarlyView.
High‐temperature interactions between low‐sulfur Al‐killed Mn–B steel and MgO–C refractories (0 and 50 wt% recyclates) are studied via finger immersion tests (1600 °C). Surface‐active elements influence infiltration. MgO/CaS layer forms, along with spinel and calcium silicate.
Matheus Roberto Bellé, Lukas Neubert, Anton Yehorov, Till M. J. Stadtmüller, Christos G. Aneziris, Olena Volkova   +5 more
wiley   +1 more source

Monocular 3D object detection with thermodynamic loss and decoupled instance depth

Connection Science
Monocular 3D detection is to obtain the 3D information of the object from the image. The mainstream methods mainly use L1 loss or L1-like loss to control the instance depth prediction. However, these methods have not achieved satisfactory results. One of
Gang Liu, Xiaoxiao Xie, Qingchen Yu
doaj   +1 more source

Influence of Sample Preparation and Processing Procedures on the Thermal Diffusivity of MgO‐C Refractories

Advanced Engineering Materials, EarlyView.
The thermal diffusivity of MgO‐C refractories is highly sensitive to sample preparation and processing procedures. In this article, the effects of coking sequence, machining conditions, structural inhomogeneity, and graphite coating application on measurements using laser flash apparatus are systematically investigated.
Luyao Pan, Rhena Wulf, Till M. J. Stadtmüller, Christos G. Aneziris, Tobias M. Fieback   +4 more
wiley   +1 more source

Versatile depth estimator based on common relative depth estimation and camera-specific relative-to-metric depth conversion

Journal of Visual Communication and Image Representation
A typical monocular depth estimator is trained for a single camera, so its performance drops severely on images taken with different cameras. To address this issue, we propose a versatile depth estimator (VDE), composed of a common relative depth estimator (CRDE) and multiple relative-to-metric converters (R2MCs).
Jinyoung Jun, Jae-Han Lee, Chang-Su Kim 0001   +2 more
openaire   +2 more sources