Saved in:
Bibliographic Details
Main Authors: Ewen, Parker, Rivkin, Dmitriy, Bijelic, Mario, Heide, Felix
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