paper-with-me

Papers

Reprojection Errors as Prompts for Efficient Scene Coordinate Regression

2024-09-06 · Ting-Ru Liu, Hsuan-Kung Yang, Jou-Min Liu, Chun-Wei Huang, Tsung-Chih Chiang, Quan Kong, Norimasa Kobori, Chun-Yi Lee

Scene coordinate regression (SCR) methods have emerged as a promising area of research due to their potential for accurate visual localization. However, many existing SCR approaches train on samples from all image regions, including dynamic objects and texture-less areas. Utilizing these areas for optimization during training can potentially hamper the overall performance and efficiency of the model. In this study, we first perform an in-depth analysis to validate the adverse impacts of these areas. Drawing inspiration from our analysis, we then introduce an error-guided feature selection (EGFS) mechanism, in tandem with the use of the Segment Anything Model (SAM). This mechanism seeds low reprojection areas as prompts and expands them into error-guided masks, and then utilizes these masks to sample points and filter out problematic areas in an iterative manner. The experiments demonstrate that our method outperforms existing SCR approaches that do not rely on 3D information on the Cambridge Landmarks and Indoor6 datasets.

📄 PDF Abstract BibTeX arXiv:2409.04178

Code (0)

등록된 구현이 없습니다.

Tasks

feature selectionregressionVisual Localization

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Scene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization

2018-08-15 · Xiaotian Li, Juha Ylioinas, Jakob Verbeek, Juho Kannala

Image-based camera relocalization is an important problem in computer vision and robotics. Recent works utilize convolutional neural networks (CNNs) to regress for pixels in a query image their corresponding 3D world coo…

Camera Relocalizationregression

PoI: Pixel of Interest for Novel View Synthesis Assisted Scene Coordinate Regression

2025-02-07 · Feifei Li, Qi Song, Chi Zhang, Hui Shuai 외

The task of estimating camera poses can be enhanced through novel view synthesis techniques such as NeRF and Gaussian Splatting to increase the diversity and extension of training data. However, these techniques often pr…

DiversityNeRFNovel View Synthesisregression

Homography-Based Loss Function for Camera Pose Regression

2022-05-04 · Clémentin Boittiaux, Ricard Marxer, Claire Dune, Aurélien Arnaubec 외

Some recent visual-based relocalization algorithms rely on deep learning methods to perform camera pose regression from image data. This paper focuses on the loss functions that embed the error between two poses to perfo…

Deep Learningregression

R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization

2025-01-02 · CVPR 2025 1 · Xudong Jiang, Fangjinhua Wang, Silvano Galliani, Christoph Vogel 외

Learning-based visual localization methods that use scene coordinate regression (SCR) offer the advantage of smaller map sizes. However, on datasets with complex illumination changes or image-level ambiguities, it remain…

Data AugmentationVisual Localization

GLACE: Global Local Accelerated Coordinate Encoding

2024-06-06 · CVPR 2024 1 · Fangjinhua Wang, Xudong Jiang, Silvano Galliani, Christoph Vogel 외

Scene coordinate regression (SCR) methods are a family of visual localization methods that directly regress 2D-3D matches for camera pose estimation. They are effective in small-scale scenes but face significant challeng…

Camera Pose EstimationPose EstimationPositionVisual Localization