How simulation helps autonomous driving: A survey of sim2real, digital twins, and parallel intelligence

X Hu, S Li, T Huang, B Tang, R Huai… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Developing autonomous driving technologies necessitates addressing safety and cost
concerns. Both academic research and commercial applications of autonomous driving …

Openscene: 3d scene understanding with open vocabularies

S Peng, K Genova, C Jiang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a
model for a single task with supervision. We propose OpenScene, an alternative approach …

Clip2scene: Towards label-efficient 3d scene understanding by clip

R Chen, Y Liu, L Kong, X Zhu, Y Ma… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

Learning 3d representations from 2d pre-trained models via image-to-point masked autoencoders

R Zhang, L Wang, Y Qiao, P Gao… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Pre-training by numerous image data has become de-facto for robust 2D representations. In
contrast, due to the expensive data processing, a paucity of 3D datasets severely hinders …

[HTML][HTML] Deep transfer learning for intelligent vehicle perception: A survey

X Liu, J Li, J Ma, H Sun, Z Xu, T Zhang, H Yu - Green Energy and Intelligent …, 2023 - Elsevier
Deep learning-based intelligent vehicle perception has been developing prominently in
recent years to provide a reliable source for motion planning and decision making in …

Unsupervised 3d perception with 2d vision-language distillation for autonomous driving

M Najibi, J Ji, Y Zhou, CR Qi, X Yan… - Proceedings of the …, 2023 - openaccess.thecvf.com
Closed-set 3D perception models trained on only a pre-defined set of object categories can
be inadequate for safety critical applications such as autonomous driving where new object …

Rangevit: Towards vision transformers for 3d semantic segmentation in autonomous driving

A Ando, S Gidaris, A Bursuc, G Puy… - Proceedings of the …, 2023 - openaccess.thecvf.com
Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, eg, via
range projection, is an effective and popular approach. These projection-based methods …

When object detection meets knowledge distillation: A survey

Z Li, P Xu, X Chang, L Yang, Y Zhang… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
Object detection (OD) is a crucial computer vision task that has seen the development of
many algorithms and models over the years. While the performance of current OD models …

Clip-fo3d: Learning free open-world 3d scene representations from 2d dense clip

J Zhang, R Dong, K Ma - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Training a 3D scene understanding model requires complicated human annotations, which
are laborious to collect and result in a model only encoding close-set object semantics. In …

Also: Automotive lidar self-supervision by occupancy estimation

A Boulch, C Sautier, B Michele… - Proceedings of the …, 2023 - openaccess.thecvf.com
We propose a new self-supervised method for pre-training the backbone of deep perception
models operating on point clouds. The core idea is to train the model on a pretext task which …