Object-Centric LiDAR-to-Radar Distillation for 3D Object Detection
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 3586-3590
Abstract
No abstract availableFunding Information
- Korea Research Institute for Defense Technology Planning and Advancement Through Defense Innovation Vanguard Enterprise Project
- Defense Acquisition Program Administration (R230206)
- Technology Innovation Program
- Ministry of Trade
- Industry & Energy (RS-2024-00445759)
- Development of Navigation Technology Utilizing Visual Information Based on Vision-Language Models for Understanding Dynamic Environments in Non-Learned Spaces
- LG AI STAR Talent Development Program for Leading Large-Scale Generative AI Models in the Physical AI Domain (RS-2025-25442149)
- Advanced GPU Utilization
- government of the Republic of Korea (02-26-01-0057)
- KENTECH research (202500007A)
- Robust Physical AI in Challenging Environments
This publication has 25 references indexed in Scilit:
- DoppDrive: Doppler-Driven Temporal Aggregation for Improved Radar Object Detection2025
- CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection2025
- RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion2025
- LEROjD: Lidar Extended Radar-Only Object Detection2024
- RadarDistill: Boosting Radar-Based Object Detection Performance via Knowledge Distillation from LiDAR Features2024
- MVFAN: Multi-view Feature Assisted Network for 4D Radar Object Detection2023
- DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation2023
- UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View2023
- PillarNet: Real-Time and High-Performance Pillar-Based 3D Object Detection2022
- nuScenes: A Multimodal Dataset for Autonomous Driving2020