paper-with-me

Papers

Scale-Free Image Keypoints Using Differentiable Persistent Homology

2024-06-03 · Giovanni Barbarani, Francesco Vaccarino, Gabriele Trivigno, Marco Guerra, Gabriele Berton, Carlo Masone

In computer vision, keypoint detection is a fundamental task, with applications spanning from robotics to image retrieval; however, existing learning-based methods suffer from scale dependency and lack flexibility. This paper introduces a novel approach that leverages Morse theory and persistent homology, powerful tools rooted in algebraic topology. We propose a novel loss function based on the recent introduction of a notion of subgradient in persistent homology, paving the way toward topological learning. Our detector, MorseDet, is the first topology-based learning model for feature detection, which achieves competitive performance in keypoint repeatability and introduces a principled and theoretically robust approach to the problem.

📄 PDF Abstract BibTeX arXiv:2406.01315

Code (1)

gbarbarani/MorseDet 공식 구현

Tasks

Image RetrievalKeypoint DetectionRetrieval

Similar Papers 제목 키워드 기반

FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation

2024-12-03 · CVPR 2025 1 · Kefan Chen, Chaerin Min, Linguang Zhang, Shreyas Hampali 외

Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a la…

Image Generation

DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection

2025-03-10 · Johan Edstedt, Georg Bökman, Mårten Wadenbäck, Michael Felsberg

Keypoints are what enable Structure-from-Motion (SfM) systems to scale to thousands of images. However, designing a keypoint detection objective is a non-trivial task, as SfM is non-differentiable. Typically, an auxiliar…

Keypoint Detectionreinforcement-learningReinforcement Learning

ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction

2021-12-06 · Xiaoming Zhao, Xingming Wu, Jinyu Miao, Weihai Chen 외

Existing methods detect the keypoints in a non-differentiable way, therefore they can not directly optimize the position of keypoints through back-propagation. To address this issue, we present a partially differentiable…

Camera Pose EstimationGPUHomography EstimationKeypoint Detection+2

Mesh deformation-based single-view 3D reconstruction of thin eyeglasses frames with differentiable rendering

2024-08-10 · Fan Zhang, Ziyue Ji, Weiguang Kang, Weiqing Li 외

With the support of Virtual Reality (VR) and Augmented Reality (AR) technologies, the 3D virtual eyeglasses try-on application is well on its way to becoming a new trending solution that offers a "try on" option to selec…

3D ReconstructionSingle-View 3D Reconstruction

RaCo: Ranking and Covariance for Practical Learned Keypoints

2026-02-17 · Abhiram Shenoi, Philipp Lindenberger, Paul-Edouard Sarlin, Marc Pollefeys arxiv

This paper introduces RaCo, a lightweight neural network designed to learn robust and versatile keypoints suitable for a variety of 3D computer vision tasks. The model integrates three key components: the repeatable keyp…

Data Augmentation