paper-with-me

홈 › Papers

EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching

2025-01-01 · CVPR 2025 1 · Dongki Jung, Jaehoon Choi, Yonghan Lee, Somi Jeong, Taejae Lee, Dinesh Manocha, Suyong Yeon

We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images, with their large fields of view, are particularly suited for dense matching techniques that aim to establish comprehensive correspondences across images. However, ERP images are subject to significant distortions, which we address by leveraging the spherical camera model and geodesic flow refinement in the dense matching method. To further mitigate these distortions, we propose spherical positional embeddings based on 3D Cartesian coordinates of the feature grid. Additionally, our method incorporates bidirectional transformations between spherical and Cartesian coordinate systems during refinement, utilizing a unit sphere to improve matching performance. We demonstrate that our proposed method achieves notable performance enhancements, with improvements of +26.72 and +42.62 in AUC@5deg on the Matterport3D and Stanford2D3D datasets. Project page: https://jdk9405.github.io/EDM

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ERP

Similar Papers 제목 키워드 기반

Equirectangular image construction method for standard CNNs for Semantic Segmentation

2023-10-13 · Haoqian Chen, Jian Liu, Minghe Li, Kaiwen Jiang 외

360{\deg} spherical images have advantages of wide view field, and are typically projected on a planar plane for processing, which is known as equirectangular image. The object shape in equirectangular images can be dist…

Data AugmentationSemantic Segmentation

SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation

2021-06-19 · CVPR 2021 1 · Giovanni Pintore, Marco Agus, Eva Almansa, Jens Schneider 외

We introduce a novel deep neural network to estimate a depth map from a single monocular indoor panorama. The network directly works on the equirectangular projection, exploiting the properties of indoor 360 images. …

Depth Estimation

ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation

2021-12-29 · Chuanqing Zhuang, Zhengda Lu, Yiqun Wang, Jun Xiao 외

Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion with equirectangular projection. In this p…

3D ReconstructionDepth Estimation

Object Detection in Equirectangular Panorama

2018-05-21 · Wenyan Yang, Yanlin Qian, Francesco Cricri, Lixin Fan 외

We introduced a high-resolution equirectangular panorama (360-degree, virtual reality) dataset for object detection and propose a multi-projection variant of YOLO detector. The main challenge with equirectangular panoram…

GPUObjectobject-detectionObject Detection

Projection-Aware End-to-End Learned Video Compression for 360-Degree Video

2026-08-26 · Niloofar Maani arxiv

360-degree video supports immersive applications such as virtual reality, autonomous driving, and education. Because spherical content cannot be processed directly by conventional video codecs, it must first be mapped to…

Autonomous Driving