Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.06332 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914455388946432 |
|---|---|
| author | Ewen, Parker Rivkin, Dmitriy Bijelic, Mario Heide, Felix |
| author_facet | Ewen, Parker Rivkin, Dmitriy Bijelic, Mario Heide, Felix |
| contents | Autonomous highway driving, especially for long-haul heavy trucks, requires detecting objects at long ranges beyond 500 meters to satisfy braking distance requirements at high speeds. At long distances, vehicles and other critical objects occupy only a few pixels in high-resolution images, causing state-of-the-art object detectors to fail. This challenge is compounded by the limited effective range of commercially available LiDAR sensors, which fall short of ultra-long range thresholds because of quadratic loss of resolution with distance, making image-based detection the most practically scalable solution given commercially available sensor constraints. We introduce Telescope, a two-stage detection model designed for ultra-long range autonomous driving. Alongside a powerful detection backbone, this model contains a novel re-sampling layer and image transformation to address the fundamental challenges of detecting small, distant objects. Telescope achieves $76\%$ relative improvement in mAP in ultra-long range detection compared to state-of-the-art methods (improving from an absolute mAP of 0.185 to 0.326 at distances beyond 250 meters), requires minimal computational overhead, and maintains strong performance across all detection ranges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06332 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection Ewen, Parker Rivkin, Dmitriy Bijelic, Mario Heide, Felix Computer Vision and Pattern Recognition Machine Learning Autonomous highway driving, especially for long-haul heavy trucks, requires detecting objects at long ranges beyond 500 meters to satisfy braking distance requirements at high speeds. At long distances, vehicles and other critical objects occupy only a few pixels in high-resolution images, causing state-of-the-art object detectors to fail. This challenge is compounded by the limited effective range of commercially available LiDAR sensors, which fall short of ultra-long range thresholds because of quadratic loss of resolution with distance, making image-based detection the most practically scalable solution given commercially available sensor constraints. We introduce Telescope, a two-stage detection model designed for ultra-long range autonomous driving. Alongside a powerful detection backbone, this model contains a novel re-sampling layer and image transformation to address the fundamental challenges of detecting small, distant objects. Telescope achieves $76\%$ relative improvement in mAP in ultra-long range detection compared to state-of-the-art methods (improving from an absolute mAP of 0.185 to 0.326 at distances beyond 250 meters), requires minimal computational overhead, and maintains strong performance across all detection ranges. |
| title | Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.06332 |