FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sonarghare, Shubham, Deshpande, Prasad, Hogan, Ciaran, Kaliappan-Mahalingam, Deepika-Rani, Sistu, Ganesh
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915630855225344
author Sonarghare, Shubham
Deshpande, Prasad
Hogan, Ciaran
Kaliappan-Mahalingam, Deepika-Rani
Sistu, Ganesh
author_facet Sonarghare, Shubham
Deshpande, Prasad
Hogan, Ciaran
Kaliappan-Mahalingam, Deepika-Rani
Sistu, Ganesh
contents Accurate BEV semantic segmentation from fisheye imagery remains challenging due to extreme non-linear distortion, occlusion, and depth ambiguity inherent to wide-angle projections. We present a distortion-aware BEV segmentation framework that directly processes multi-camera high-resolution fisheye images,utilizing calibrated geometric unprojection and per-pixel depth distribution estimation. Each image pixel is lifted into 3D space via Gaussian parameterization, predicting spatial means and anisotropic covariances to explicitly model geometric uncertainty. The projected 3D Gaussians are fused into a BEV representation via differentiable splatting, producing continuous, uncertainty-aware semantic maps without requiring undistortion or perspective rectification. Extensive experiments demonstrate strong segmentation performance on complex parking and urban driving scenarios, achieving IoU scores of 87.75% for drivable regions and 57.26% for vehicles under severe fisheye distortion and diverse environmental conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17210
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception
Sonarghare, Shubham
Deshpande, Prasad
Hogan, Ciaran
Kaliappan-Mahalingam, Deepika-Rani
Sistu, Ganesh
Computer Vision and Pattern Recognition
Accurate BEV semantic segmentation from fisheye imagery remains challenging due to extreme non-linear distortion, occlusion, and depth ambiguity inherent to wide-angle projections. We present a distortion-aware BEV segmentation framework that directly processes multi-camera high-resolution fisheye images,utilizing calibrated geometric unprojection and per-pixel depth distribution estimation. Each image pixel is lifted into 3D space via Gaussian parameterization, predicting spatial means and anisotropic covariances to explicitly model geometric uncertainty. The projected 3D Gaussians are fused into a BEV representation via differentiable splatting, producing continuous, uncertainty-aware semantic maps without requiring undistortion or perspective rectification. Extensive experiments demonstrate strong segmentation performance on complex parking and urban driving scenarios, achieving IoU scores of 87.75% for drivable regions and 57.26% for vehicles under severe fisheye distortion and diverse environmental conditions.
title FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.17210