Related papers: RSD-DOG : A New Image Descriptor based on Second Order Derivatives

RSD-DOG : A New Image Descriptor based on Second Order Derivatives

URL: http://arxiv.org/abs/2408.07687v1
Date: Wed, 14 Aug 2024 17:41:45 GMT
Title: RSD-DOG : A New Image Descriptor based on Second Order Derivatives
Authors: Darshan Venkatrayappa, Philippe Montesinos, Daniel Diep, Baptiste Magnier,
Abstract summary: This paper introduces the new and powerful image patch descriptor based on second order image statistics/derivatives. The considered 3D surface has a rich set of second order features/statistics such as ridges, valleys, cliffs and so on. The obtained descriptor shows a good discriminative power when dealing with the variations in illumination, scale, rotation, blur, viewpoint and compression.
Score: 2.174919458782602
License: http://creativecommons.org/licenses/by/4.0/
Abstract: This paper introduces the new and powerful image patch descriptor based on second order image statistics/derivatives. Here, the image patch is treated as a 3D surface with intensity being the 3rd dimension. The considered 3D surface has a rich set of second order features/statistics such as ridges, valleys, cliffs and so on, that can be easily captured by using the difference of rotating semi Gaussian filters. The originality of this method is based on successfully combining the response of the directional filters with that of the Difference of Gaussian (DOG) approach. The obtained descriptor shows a good discriminative power when dealing with the variations in illumination, scale, rotation, blur, viewpoint and compression. The experiments on image matching, demonstrates the advantage of the obtained descriptor when compared to its first order counterparts such as SIFT, DAISY, GLOH, GIST and LIDRIC.

Related papers

Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference [62.99706119370521]
Humans can easily deduce the relative pose of an unseen object, without label/training, given only a single query-reference image pair. We propose a novel 3D generalizable relative pose estimation method by elaborating (i) with a 2.5D shape from an RGB-D reference, (ii) with an off-the-shelf differentiable, and (iii) with semantic cues from a pretrained model like DINOv2.
arXiv Detail & Related papers (2024-06-26T16:01:10Z)
NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows [60.291277312569285]
We present a method for automatically modifying a NeRF representation based on a single observation. Our method defines the transformation as a 3D flow, specifically as a weighted linear blending of rigid transformations. We also introduce a new dataset for exploring the problem of modifying a NeRF scene through a single observation.
arXiv Detail & Related papers (2024-06-15T07:58:08Z)
TP3M: Transformer-based Pseudo 3D Image Matching with Reference Image [0.9831489366502301]
We propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from the source image to 3D features with the help of a reference image and matches to the 2D features extracted from the destination image. Experimental results on multiple datasets show that the proposed method achieves the state-of-the-art on the tasks of homography estimation, pose estimation and visual localization.
arXiv Detail & Related papers (2024-05-14T08:56:09Z)
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization [62.13932669494098]
This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to factorize the scene into material properties, light, and geometry. We compute the normal of each 3D Gaussian using the shortest eigenvector, with a directional masking scheme forcing accurate normal estimation without external supervision. We adopt an efficient voxel-based indirect illumination tracing scheme that stores direction-aware outgoing radiance in each 3D Gaussian to disentangle secondary illumination for approximating multi-bounce light transport.
arXiv Detail & Related papers (2023-12-08T16:05:15Z)
Registering Image Volumes using 3D SIFT and Discrete SP-Symmetry [2.1829116024916844]
A binary feature sign $s in -1,+1$ is defined as the sign of the Laplacian operator $nabla2$. A 3D parity transforms $(x,y,z)rightarrow(-x,-y,-z)$ transforms $(x,y,z)rightarrow(-x,-y,-z)$, i.e. SP-invariant or SP-symmetric.
arXiv Detail & Related papers (2022-05-30T22:57:55Z)
Extreme Rotation Estimation using Dense Correlation Volumes [73.35119461422153]
We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting. We observe that, even when images do not overlap, there may be rich hidden cues as to their geometric relationship. We propose a network design that can automatically learn such implicit cues by comparing all pairs of points between the two input images.
arXiv Detail & Related papers (2021-04-28T02:00:04Z)
Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild [96.09941542587865]
We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.
arXiv Detail & Related papers (2020-07-17T12:34:38Z)
Coarse-to-Fine Gaze Redirection with Numerical and Pictorial Guidance [74.27389895574422]
We propose a novel gaze redirection framework which exploits both a numerical and a pictorial direction guidance. The proposed method outperforms the state-of-the-art approaches in terms of both image quality and redirection precision.
arXiv Detail & Related papers (2020-04-07T01:17:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.