Deep depth completion from extremely sparse data: A survey

J Hu, C Bao, M Ozay, C Fan, Q Gao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map
captured from a depth sensor, eg, LiDARs. It plays an essential role in various applications …

Self-supervised multimodal learning: A survey

Y Zong, O Mac Aodha, T Hospedales - arXiv preprint arXiv:2304.01008, 2023 - arxiv.org
Multimodal learning, which aims to understand and analyze information from multiple
modalities, has achieved substantial progress in the supervised regime in recent years …

Bridging the domain gap: Self-supervised 3d scene understanding with foundation models

Z Chen, L Jing, Y Li, B Li - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Foundation models have achieved remarkable results in 2D and language tasks like image
segmentation, object detection, and visual-language understanding. However, their …

Camliflow: bidirectional camera-lidar fusion for joint optical flow and scene flow estimation

H Liu, T Lu, Y Xu, J Liu, W Li… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
In this paper, we study the problem of jointly estimating the optical flow and scene flow from
synchronized 2D and 3D data. Previous methods either employ a complex pipeline that …

Real time object detection using LiDAR and camera fusion for autonomous driving

H Liu, C Wu, H Wang - Scientific Reports, 2023 - nature.com
Autonomous driving has been widely applied in commercial and industrial applications,
along with the upgrade of environmental awareness systems. Tasks such as path planning …

Naruto: Neural active reconstruction from uncertain target observations

Z Feng, H Zhan, Z Chen, Q Yan, X Xu… - Proceedings of the …, 2024 - openaccess.thecvf.com
We present NARUTO a neural active reconstruction system that combines a hybrid neural
representation with uncertainty learning enabling high-fidelity surface reconstruction. Our …

CVRecon: Rethinking 3d geometric feature learning for neural reconstruction

Z Feng, L Yang, P Guo, B Li - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Recent advances in neural reconstruction using posed image sequences have made
remarkable progress. However, due to the lack of depth information, existing volumetric …

Learning optical flow and scene flow with bidirectional camera-lidar fusion

H Liu, T Lu, Y Xu, J Liu, L Wang - IEEE Transactions on Pattern …, 2023 - ieeexplore.ieee.org
In this paper, we study the problem of jointly estimating the optical flow and scene flow from
synchronized 2D and 3D data. Previous methods either employ a complex pipeline that …

Point cloud self-supervised learning via 3d to multi-view masked autoencoder

Z Chen, Y Li, L Jing, L Yang, B Li - arXiv preprint arXiv:2311.10887, 2023 - arxiv.org
In recent years, the field of 3D self-supervised learning has witnessed significant progress,
resulting in the emergence of Multi-Modality Masked AutoEncoders (MAE) methods that …

A comprehensive survey of depth completion approaches

MAU Khan, D Nazir, A Pagani, H Mokayed, M Liwicki… - Sensors, 2022 - mdpi.com
Depth maps produced by LiDAR-based approaches are sparse. Even high-end LiDAR
sensors produce highly sparse depth maps, which are also noisy around the object …