LabelDistill: Label-Guided Cross-Modal Knowledge Distillation for Camera-Based 3D Object Detection

S Kim, Y Kim, S Hwang, H Jeong, D Kum - European Conference on …, 2025 - Springer
Recent advancements in camera-based 3D object detection have introduced cross-modal
knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging …

SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects

A Kumar, Y Guo, X Huang, L Ren… - Proceedings of the …, 2024 - openaccess.thecvf.com
Monocular 3D detectors achieve remarkable performance on cars and smaller objects.
However their performance drops on larger objects leading to fatal accidents. Some attribute …

TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation

S Xu, F Li, P Huang, Z Song, ZX Yang - arXiv preprint arXiv:2412.20911, 2024 - arxiv.org
Accurate multi-view 3D object detection is essential for applications such as autonomous
driving. Researchers have consistently aimed to leverage LiDAR's precise spatial …

Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection

G Chang, J Lee, D Kim, J Kim, D Lee, D Ji… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advances in 3D object detection leveraging multi-view cameras have demonstrated
their practical and economical value in various challenging vision tasks. However, typical …

Instance-wise Knowledge Enhancement for 3D Instance Segmentation

W Roh, H Jung, G Nam, DI Lee, H Park, SH Yoon… - openreview.net
Recent 3D Instance Segmentation methods typically follow a similar paradigm; they encode
hundreds of instance-wise candidates with instance-specific information in various ways and …

D3pd: Dual Distillation and Dynamic Fusion of Camera and Radar for 3d Perception Detection

S Xiong - papers.ssrn.com
Autonomous driving sensing capability is driving the rapid development of BEV technology.
Using a combination of surround-view images and Radar is seen as a more cost-friendly …