mlsanityData to 7 Oct 2026

Convolution kernel adaptation to calibrated fisheye

arXiv 2402.01456 ↗First posted 2 Feb 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Convolution kernels are the basic structural component of convolutional neural networks (CNNs). In the last years there has been a growing interest in fisheye cameras for many applications. However, the radially symmetric projection model of these cameras produces high distortions that affect the performance of CNNs, especially when the field of view is very large. In this work, we tackle this problem by proposing a method that leverages the calibration of cameras to deform the convolution kernel accordingly and adapt to the distortion. That way, the receptive field of the convolution is similar to standard convolutions in perspective images, allowing us to take advantage of pre-trained networks in large perspective datasets. We show how, with just a brief fine-tuning stage in a small dataset, we improve the performance of the network for the calibrated fisheye with respect to standard convolutions in depth estimation and semantic segmentation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

22 of 33 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2017Deformable Convolutional Networkscited by 1,481
  4. 2018Spherical CNNscited by 452
  5. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  6. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  7. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  8. 2018OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramascited by 98
  9. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 91
  10. 2019Spherical CNNs on Unstructured Gridscited by 76
  11. 2019CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthcited by 75
  12. 2022OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusioncited by 60
10 more
  1. 2019Corners for Layout: End-to-End Layout Recovery from 360 Imagescited by 55
  2. 2019Spherical View Synthesis for Self-Supervised 360 Depth Estimationcited by 51
  3. 2022Review on Panoramic Imaging and Its Applications in Scene Understandingcited by 42
  4. 2021ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimationcited by 39
  5. 2017Active Convolution: Learning the Shape of Convolution for Image Classificationcited by 24
  6. 2018Monocular Fisheye Camera Depth Estimation Using Sparse LiDAR Supervisioncited by 19
  7. 2019What's in my Room? Object Recognition on Indoor Panoramic Imagescited by 16
  8. 2018End to End Vehicle Lateral Control Using a Single Fisheye Cameracited by 13
  9. 2022FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutionscited by 11
  10. 2018Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Imagescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 17
  2. 2026Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Camerascited by 0
  3. 2026Geometry-Aware Fisheye-LiDAR Fusion for Robust 3D Object Detection in Low-Overlap Setupscited by 0
  4. 2026From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentationcited by 0