Are we ready for vision-centric driving streaming perception? the asap benchmark

X Wang, Z Zhu, Y Zhang, G Huang… - Proceedings of the …, 2023 - openaccess.thecvf.com
In recent years, vision-centric perception has flourished in various autonomous driving tasks,
including 3D detection, semantic map construction, motion forecasting, and depth …

FADM-SLAM: A fast and accurate dynamic intelligent motion SLAM for autonomous robot exploration involving movable objects

QU Islam, H Ibrahim, PK Chin, K Lim… - Robotic Intelligence and …, 2023 - emerald.com
Purpose Many popular simultaneous localization and mapping (SLAM) techniques have low
accuracy, especially when localizing environments containing dynamically moving objects …

Mono-ViFI: A Unified Learning Framework for Self-supervised Single and Multi-frame Monocular Depth Estimation

J Liu, L Kong, B Li, Z Wang, H Gu, J Chen - European Conference on …, 2025 - Springer
Self-supervised monocular depth estimation has gathered notable interest since it can
liberate training from dependency on depth annotations. In monocular video training case …

M Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation

Y Zou, Y Ding, X Qiu, H Wang, H Zhang - European Conference on …, 2025 - Springer
This paper presents a novel self-supervised two-frame multi-camera metric depth estimation
network, termed M\({^ 2}\) Depth, which is designed to predict reliable scale-aware …

Self-Supervised Monocular Depth Estimation With Positional Shift Depth Variance and Adaptive Disparity Quantization

JLG Bello, J Moon, M Kim - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
Recently, attempts to learn the underlying 3D structures of a scene from monocular videos in
a fully self-supervised fashion have drawn much attention. One of the most challenging …

Self-supervised multi-frame depth estimation with visual-inertial pose transformer and monocular guidance

X Wang, H Luo, Z Wang, J Zheng, X Bai - Information Fusion, 2024 - Elsevier
Self-supervised monocular depth estimation has been a popular topic since it does not need
labor-intensive depth ground truth collection. However, the accuracy of monocular network …

Monocular depth estimation via self-supervised self-distillation

H Hu, Y Feng, D Li, S Zhang, H Zhao - Sensors, 2024 - mdpi.com
Self-supervised monocular depth estimation can exhibit excellent performance in static
environments due to the multi-view consistency assumption during the training process …

Exploring the mutual influence between self-supervised single-frame and multi-frame depth estimation

J Xiang, Y Wang, L An, H Liu… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
Although both self-supervised single-frame and multi-frame depth estimation methods only
require unlabeled monocular videos for training, the information they leverage varies …

SIM-MultiDepth: Self-Supervised Indoor Monocular Multi-Frame Depth Estimation Based on Texture-Aware Masking

X Guo, H Zhao, S Shao, X Li, B Zhang, N Li - Remote Sensing, 2024 - mdpi.com
Self-supervised monocular depth estimation methods have become the focus of research
since ground truth data are not required. Current single-image-based works only leverage …

Exploring Few-Beam LiDAR Assistance in Self-Supervised Multi-Frame Depth Estimation

R Fan, M Poggi, S Mattoccia - 2024 IEEE/RSJ International …, 2024 - ieeexplore.ieee.org
Self-supervised multi-frame depth estimation methods only require unlabeled monocular
videos for training. However, most existing methods face challenges, including accuracy …