Localbins: Improving depth estimation by learning local distributions

SF Bhat, I Alhashim, P Wonka - European Conference on Computer Vision, 2022 - Springer
We propose a novel architecture for depth estimation from a single image. The architecture
itself is based on the popular encoder-decoder architecture that is frequently used as a …

DARE-GRAM: Unsupervised domain adaptation regression by aligning inverse gram matrices

I Nejjar, Q Wang, O Fink - … of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
Abstract Unsupervised Domain Adaptation Regression (DAR) aims to bridge the domain
gap between a labeled source dataset and an unlabelled target dataset for regression …

Towards open-world recognition: Critical problems and challenges

K Wang, Z Li, Y Chen, W Dong, J Chen - Engineering Applications of …, 2025 - Elsevier
With the emergence of rich classification models and high computing power, recognition
systems are widely used in various fields. Unfortunately, as the scale of open systems …

[HTML][HTML] Deep learning of monocular depth, optical flow and ego-motion with geometric guidance for UAV navigation in dynamic environments

F Mumuni, A Mumuni, CK Amuzuvi - Machine Learning with Applications, 2022 - Elsevier
Computer vision-based depth estimation and visual odometry provide perceptual
information useful for robot navigation tasks like obstacle avoidance. However, despite the …

Learning feature decomposition for domain adaptive monocular depth estimation

SY Lo, W Wang, J Thomas, J Zheng… - 2022 IEEE/RSJ …, 2022 - ieeexplore.ieee.org
Monocular depth estimation (MDE) has attracted intense study due to its low cost and critical
functions for robotic tasks such as localization, map** and obstacle detection. Supervised …

Transfer multi-source knowledge via scale-aware online domain adaptation in depth estimation for autonomous driving

PTH Thanh, MQV Bui, DD Nguyen, TV Pham… - Image and Vision …, 2024 - Elsevier
This paper deals with the challenging online monocular depth adaptation task that aims to
train an initial depth estimation model in a source domain and continuously adapt the model …

Calibrating Panoramic Depth Estimation for Practical Localization and Map**

J Kim, ES Lee, YM Kim - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
The absolute depth values of surrounding environments provide crucial cues for various
assistive technologies, such as localization, navigation, and 3D structure estimation. We …

Visual–tactile learning of robotic cable-in-duct installation skills

B Duan, K Qian, A Liu, S Luo - Automation in Construction, 2025 - Elsevier
Cable-in-duct installation is one of the most challenging contact-rich interior finishing tasks
for construction robots. Such precise robotic cable manipulation skills are expected to be …

Dimix: Disentangle-and-mix based domain generalizable medical image segmentation

H Kim, Y Shin, D Hwang - … Conference on Medical Image Computing and …, 2023 - Springer
The rapid advancements in deep learning have revolutionized multiple domains, yet the
significant challenge lies in effectively applying this technology to novel and unfamiliar …

BYEL: Bootstrap Your Emotion Latent

H Lee, H Lim, S Lim - European Conference on Computer Vision, 2022 - Springer
With the improved performance of deep learning, the number of studies trying to apply deep
learning to human emotion analysis is increasing rapidly. But even with this trend, it is still …