Saved in:
Bibliographic Details
Main Authors: Sun, Huawei, Sahin, Bora Kunter, Stettinger, Georg, Bernhard, Maximilian, Schubert, Matthias, Wille, Robert
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.03679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915275550490624
author Sun, Huawei
Sahin, Bora Kunter
Stettinger, Georg
Bernhard, Maximilian
Schubert, Matthias
Wille, Robert
author_facet Sun, Huawei
Sahin, Bora Kunter
Stettinger, Georg
Bernhard, Maximilian
Schubert, Matthias
Wille, Robert
contents Segmenting objects in an environment is a crucial task for autonomous driving and robotics, as it enables a better understanding of the surroundings of each agent. Although camera sensors provide rich visual details, they are vulnerable to adverse weather conditions. In contrast, radar sensors remain robust under such conditions, but often produce sparse and noisy data. Therefore, a promising approach is to fuse information from both sensors. In this work, we propose a novel framework to enhance camera-only baselines by integrating a diffusion model into a camera-radar fusion architecture. We leverage radar point features to create pseudo-masks using the Segment-Anything model, treating the projected radar points as point prompts. Additionally, we propose a noise reduction unit to denoise these pseudo-masks, which are further used to generate inpainted images that complete the missing information in the original images. Our method improves the camera-only segmentation baseline by 2.63% in mIoU and enhances our camera-radar fusion architecture by 1.48% in mIoU on the Waterscenes dataset. This demonstrates the effectiveness of our approach for semantic segmentation using camera-radar fusion under adverse weather conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03679
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CaRaFFusion: Improving 2D Semantic Segmentation with Camera-Radar Point Cloud Fusion and Zero-Shot Image Inpainting
Sun, Huawei
Sahin, Bora Kunter
Stettinger, Georg
Bernhard, Maximilian
Schubert, Matthias
Wille, Robert
Computer Vision and Pattern Recognition
Segmenting objects in an environment is a crucial task for autonomous driving and robotics, as it enables a better understanding of the surroundings of each agent. Although camera sensors provide rich visual details, they are vulnerable to adverse weather conditions. In contrast, radar sensors remain robust under such conditions, but often produce sparse and noisy data. Therefore, a promising approach is to fuse information from both sensors. In this work, we propose a novel framework to enhance camera-only baselines by integrating a diffusion model into a camera-radar fusion architecture. We leverage radar point features to create pseudo-masks using the Segment-Anything model, treating the projected radar points as point prompts. Additionally, we propose a noise reduction unit to denoise these pseudo-masks, which are further used to generate inpainted images that complete the missing information in the original images. Our method improves the camera-only segmentation baseline by 2.63% in mIoU and enhances our camera-radar fusion architecture by 1.48% in mIoU on the Waterscenes dataset. This demonstrates the effectiveness of our approach for semantic segmentation using camera-radar fusion under adverse weather conditions.
title CaRaFFusion: Improving 2D Semantic Segmentation with Camera-Radar Point Cloud Fusion and Zero-Shot Image Inpainting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.03679