EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching

Input (c) EDM (ours) Warp (b) Prev. SotA with Cubemap Proj. Warp Multiple Predictions (a) Prev. SotA Warp Figure 1. (a) Previous state-of-the-art [15] struggles to achieve accurate dense matching in equirectangular projection (ERP) images due to inherent distortions. (b) The ERP image can be transformed into a cubemap image, which consists of six perspective images. However, this approach demands multiple independent iterations of inference for each pair of perspective images, increasing computational complexity and losing the global information in the ERP image. (c) Our proposed method, EDM, leverages the spherical camera model, rendering it robust against distortions. Warp refers to results obtained by multiplying the warped image with the predicted certainty map, demonstrating that our method yields more accurate dense matches.