Papers for

automotive perception engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Agent-wise normalization improves vehicle perception with corrupted collaborators

Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators

Abstract: Intermediate-fusion cooperative perception lets a vehicle detect objects beyond its own field of view by fusing features shared by nearby agents. When only a collaborator's cameras are degraded by fog, motion blur or exposure errors, the features it shares drift away from the training distribution while the ego input stays clean, and cooperation can become worse than not cooperating at all. Test-time batch-normalization adaptation, the standard training-free remedy, estimates statistics over the pooled batch of all agents and therefore normalizes both the clean ego and the corrupted collaborator with a mixture of two distributions. We show that this mixing harms even the clean ego: when the ego shares BN statistics with a corrupted collaborator, its detection from its own features drops by 3.58 to 6.68 AP@0.5 points although its cameras are untouched. We propose AgentNorm, an agent-wise test-time normalization that i) estimates the normalization statistics of every collaborator from its own current observation and ii) anchors the ego to its source statistics, so that the ego path remains exactly the original model. AgentNorm has no learnable parameters, needs no gradients or labels, is independent of the order of test frames, and runs locally on each agent without changing the transmitted features. On camera-based OPV2V with four fusion checkpoints and collaborator-only corruptions, AgentNorm raises AP@0.5 under severity-5 fog from 29.42-37.25 to 43.32-58.86 and outperforms pooled normalization by 5.53-12.94 points under fog and motion blur, at an extra latency of 2.3 ms per frame. On the real-world DAIR-V2X-C dataset, it outperforms pooled normalization in all ten infrastructure-corruption settings. We also report the cases it does not fix: occlusion, which removes image content rather than shifting feature statistics, and the case in which all agents share the same shift.

Thu 29 OctComputer Vision and Pattern RecognitionArtificial Intelligence
The gist
Vehicles can work together to detect objects beyond what their own cameras see by sharing information. However, when a collaborating vehicle has foggy or blurry cameras, its shared data can confuse the main vehicle's system, making detection worse. The authors propose a way to normalize each vehicle’s data separately, so the main vehicle’s clean input is not mixed with corrupted data. This method improves object detection performance in tough conditions like fog and blur without needing retraining or extra labels.
Open → 2610.39505v1

Fisheye camera detection improved with minimal retraining steps

FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters

Abstract: Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial distortion warps local image structure, while boundary compression shrinks objects to near-invisible sizes. Full fine-tuning closes much of the gap but requires abundant fisheye labels and compute. We present FUSEye, a training-light framework that turns a frozen-backbone COCO-pretrained extra-large YOLO26 detector (YOLO26-x) into a fisheye detector. FUSEye adds roughly 227k new parameters while updating the inserted modules and the pretrained detection head. It addresses the transfer gap at three causally linked levels. At the input level, overlapping grid view generation and box remapping (GridViews) enlarge compressed boundary regions. At the feature level, zero-initialized residual adapters (Z-Adapters) correct distortion-induced feature misalignment. At the decision level, learned cross-projection agreement fusion (AgreeFusion) promotes low-confidence detections only when they are supported by consistent evidence across multiple views. On the WoodScape surround-view fisheye benchmark, FUSEye raises YOLO26-x from 0.148 to 0.266 mAP50 and retains 84.3% fully fine-tuned accuracy. Moreover, randomly using only 25% of the labeled training images, FUSEye achieves 0.2597 mAP50, retaining 97.6% of its full-label performance. FUSEye also consistently improves YOLOv8-11 detectors, showing that the recipe is architecture-agnostic. Source code will be available at https://github.com/Su-wenya/FUSEye.

Fri 2 OctComputer Vision and Pattern RecognitionRobotics
The gist
Detecting objects in images from fisheye cameras is hard because the curved lens distorts what the camera sees, especially near the edges. The authors propose FUSEye, a method that tweaks a popular object detector with only a small number of new parts and training steps to handle these distortions better. They improve detection accuracy significantly, even when using much less labeled training data. Their approach works across different detection models and keeps the original detector mostly unchanged.
Open → 2610.02799v1