The paper introduces Post Fusion Stabilizer (PFS), a lightweight module that refines intermediate bird’s‑eye view (BEV) feature maps in existing camera‑LiDAR fusion detectors. PFS stabilizes feature statistics under domain shift, suppresses regions affected by sensor degradation, and adaptively restores weakened cues via residual correction, acting as a near‑identity transformation. On the nuScenes benchmark, PFS achieves state‑of‑the‑art robustness, notably improving camera dropout robustness by +1.2% and low‑light performance by +4.4% mAP while adding only 3.3 M parameters.
By Trung Tien Dong, Dev Thakkar, Arman Sargolzaei, Xiaomin Lin
The paper introduces Variance‑Guided Spatial Attention Fusion (VG‑SAF), a method for robust end‑to‑end driving that fuses camera and LiDAR data while handling asymmetric sensor degradation. VG‑SAF uses a physically grounded augmentor to generate dense reliability masks, modality‑specific experts to predict per‑pixel reliability scales, and a hybrid attention mechanism that gates unreliable cells and balances modalities. The approach also includes a Laplace uncertainty head to signal severe or combined sensor failures, and demonstrates improved closed‑loop robustness on the CARLA Longest6 benchmark across various degradation scenarios.
By Weizhi Tao, Zengwang Jin, Xiao Wang, Hailong Huang
End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines remain fragile under asymmetric sensor degradation, where either an entire modality or only...
SARFusion introduces a scene-aware routing approach for camera‑LiDAR 3D object detection, decoupling object‑query decoding into separate camera, LiDAR, and fusion branches. By estimating a global scene reliability prior and incorporating object‑level evidence, each query is routed to the most suitable branch, reducing cross‑modal interference. The method achieves strong performance on the nuScenes test set (72.5 mAP, 74.4 NDS) and demonstrates robustness to sensor corruptions and environmental changes.
By Yuting Zhao, Ziyi Zheng, Shuxiao Li
arXiv:2602. 19349v2 Announce Type: replace-cross Abstract: LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode.
By Rohit Mohan, Florian Drews, Yakov Miron, Daniele Cattaneo, Abhinav Valada
The paper introduces SR‑BEVS, a sparse recovery learning technique that enhances both clean accuracy and robustness to real‑world corruptions for camera‑based bird’s‑eye view (BEV) 3D object detection models. By pruning weights based on magnitude, generating diverse sparse models, retraining them with varied learning rates, and averaging the recovered models into a single dense model, the method achieves up to 33.8% improvement in corruption robustness and a 1.8% gain in clean accuracy over the Fast‑BEV baseline on the nuScenes dataset. The approach adds no inference overhead and preserves a connected low‑loss basin, suggesting applicability to other BEV models.
By Jinwoo Chung, Sangho An, Hyunsung Park, Jangho Kim
Multi-modality data from different sensors provides rich complementary information for 3D perception, becoming an essential component in reliable autonomous driving systems. Current research typically designs intricate and complex fusion strategies to integrate information from multimodal data on a unified bird's-eye-view (BEV) feature map for the joint learning of multiple perception tasks.
arXiv:2606. 01277v1 Announce Type: cross Abstract: Current end-to-end autonomous driving systems predominantly rely on frame-based sensors, which suffer from inherent perception latency and motion blur during highly dynamic encounters, specifically sudden pedestrian crossings.
By Oskar Natan, Andi Dharmawan, Aufaclav Zatu Kusuma Frisky, Jazi Eko Istiyanto, Jun Miura
CalibSwitch is an observation‑driven framework for Camera–LiDAR perception that separates absolute extrinsic recovery from selective state maintenance. It introduces a cross‑modal absolute extrinsic generator (CAEG) that recovers full SE(3) candidates from image–point observations without needing an initial transform, and a selective recurrent calibration policy (SRCP) that decides when to update the working geometry based on observation quality and temporal history. On the nuScenes dataset, CAEG achieves mean translation and rotation errors of 0.248 m and 5.884°, while SRCP reduces composite error to 1.46 with only 9.70 % candidate commitments, improving frozen‑detector mAP and NDS by 1.43 and 0.92 points respectively.
By Haifa Zhang, Yijing Wang, Zhiqiang Zuo
arXiv:2601. 20720v2 Announce Type: replace-cross Abstract: End-to-end perception and trajectory prediction from raw sensor data is one of the key capabilities for autonomous driving.
By Matej Halinkovic, Nina Masarykova, Alexey Vinel, Marek Galinski
arXiv:2607. 04541v1 Announce Type: cross Abstract: Camera-radar (CR) fusion is a practical sensing configuration for autonomous driving, but existing models are typically trained with task-specific supervision, limiting reusable representation learning.
By Jingyu Song, Yi Liu, Katherine A. Skinner
arXiv:2606. 02979v1 Announce Type: cross Abstract: We present a novel compact deep multi-task learning model to handle various autonomous driving perception tasks in one forward pass.
By Oskar Natan, Jun Miura