Robustness-aware 3d object detection in autonomous driving: A review and outlook

Z Song, L Liu, F Jia, Y Luo, C Jia… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

Latr: 3d lane detection from monocular images with transformer

Y Luo, C Zheng, X Yan, T Kun… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract 3D lane detection from monocular images is a fundamental yet challenging task in
autonomous driving. Recent advances primarily rely on structural 3D surrogates (eg, bird's …

Pyra: Parallel yielding re-activation for training-inference efficient task adaptation

Y Xiong, H Chen, T Hao, Z Lin, J Han, Y Zhang… - … on Computer Vision, 2025 - Springer
Recently, the scale of transformers has grown rapidly, which introduces considerable
challenges in terms of training overhead and inference efficiency in the scope of task …

Llmi3d: Empowering llm with 3d perception from a single 2d image

F Yang, S Zhao, Y Zhang, H Chen, H Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advancements in autonomous driving, augmented reality, robotics, and embodied
intelligence have necessitated 3D perception algorithms. However, current 3D perception …

MonoCD: Monocular 3D Object Detection with Complementary Depths

L Yan, P Yan, S Xiong, X Xiang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Monocular 3D object detection has attracted widespread attention due to its potential to
accurately obtain object 3D localization from a single image at a low cost. Depth estimation …

Geometry-Guided Domain Generalization for Monocular 3D Object Detection

F Yang, H Chen, Y He, S Zhao, C Zhang, K Ni… - Proceedings of the …, 2024 - ojs.aaai.org
Monocular 3D object detection (M3OD) is important for autonomous driving. However,
existing deep learning-based methods easily suffer from performance degradation in real …

High-order Structural Relation Distillation Networks from LiDAR to Monocular Image 3D Detectors

W Yan, L Xu, H Liu, C Tang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
3D object detection is a crucial and complex undertaking in the realm of 3D scene
comprehension. Monocular-based 3D detectors, in comparison to LiDAR 3D detectors that …

YOLO-UniOW: Efficient Universal Open-World Object Detection

L Liu, J Feng, H Chen, A Wang, L Song, J Han… - arXiv preprint arXiv …, 2024 - arxiv.org
Traditional object detection models are constrained by the limitations of closed-set datasets,
detecting only categories encountered during training. While multimodal models have …

HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator

F Yang, R Zhen, J Wang, Y Zhang, H Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
AIGC images are prevalent across various fields, yet they frequently suffer from quality
issues like artifacts and unnatural textures. Specialized models aim to predict defect region …