{"ID":2828118,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.15581","arxiv_id":"2512.15581","title":"IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion","abstract":"High-performance Radar-Camera 3D object detection can be achieved by leveraging knowledge distillation without using LiDAR at inference time. However, existing distillation methods typically transfer modality-specific features directly to each sensor, which can distort their unique characteristics and degrade their individual strengths. To address this, we introduce IMKD, a radar-camera fusion framework based on multi-level knowledge distillation that preserves each sensor's intrinsic characteristics while amplifying their complementary strengths. IMKD applies a three-stage, intensity-aware distillation strategy to enrich the fused representation across the architecture: (1) LiDAR-to-Radar intensity-aware feature distillation to enhance radar representations with fine-grained structural cues, (2) LiDAR-to-Fused feature intensity-guided distillation to selectively highlight useful geometry and depth information at the fusion level, fostering complementarity between the modalities rather than forcing them to align, and (3) Camera-Radar intensity-guided fusion mechanism that facilitates effective feature alignment and calibration. Extensive experiments on the nuScenes benchmark show that IMKD reaches 67.0% NDS and 61.0% mAP, outperforming all prior distillation-based radar-camera fusion methods. Our code and models are available at https://github.com/dfki-av/IMKD/.","short_abstract":"High-performance Radar-Camera 3D object detection can be achieved by leveraging knowledge distillation without using LiDAR at inference time. However, existing distillation methods typically transfer modality-specific features directly to each sensor, which can distort their unique characteristics and degrade their ind...","url_abs":"https://arxiv.org/abs/2512.15581","url_pdf":"https://arxiv.org/pdf/2512.15581v1","authors":"[\"Shashank Mishra\",\"Karan Patil\",\"Didier Stricker\",\"Jason Rambach\"]","published":"2025-12-17T16:40:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":605851,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2828118,"paper_url":"https://arxiv.org/abs/2512.15581","paper_title":"IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion","repo_url":"https://github.com/dfki-av/IMKD","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}