HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

• URL: http://arxiv.org/abs/2305.03595v1
• Date: Fri, 5 May 2023 15:00:14 GMT
• Title: HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer
• Authors: Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Yi Zhao, Giorgos Tolias, Juho Kannala
• Abstract summary: We present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image. The proposed method, which is an extension of HSCNet, allows us to train compact models which scale robustly to large environments.
• Score: 23.920690073252636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, deep neural networks have been exploited to regress the mapping between raw pixels and 3D coordinates in the scene, and thus the matching is implicitly performed by the forward pass through the network. However, in a large and ambiguous environment, learning such a regression task directly can be difficult for a single network. In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image. The proposed method, which is an extension of HSCNet, allows us to train compact models which scale robustly to large environments. It sets a new state-of-the-art for single-image localization on the 7-Scenes, 12 Scenes, Cambridge Landmarks datasets, and the combined indoor scenes.

Related papers

• GLACE: Global Local Accelerated Coordinate Encoding [66.87005863868181]
  Scene coordinate regression methods are effective in small-scale scenes but face significant challenges in large-scale scenes. We propose GLACE, which integrates pre-trained global and local encodings and enables SCR to scale to large scenes with only a single small-sized network. Our method achieves state-of-the-art results on large-scale scenes with a low-map-size model.
  arXiv  Detail & Related papers  (2024-06-06T17:59:50Z)
• SACReg: Scene-Agnostic Coordinate Regression for Visual Localization [16.866303169903237]
  We propose a generalized SCR model trained once in new test scenes, regardless of their scale, without any finetuning. Instead of encoding the scene coordinates into the network weights, our model takes as input a database image with some sparse 2D pixel to 3D coordinate annotations. We show that the database representation of images and their 2D-3D annotations can be highly compressed with negligible loss of localization performance.
  arXiv  Detail & Related papers  (2023-07-21T16:56:36Z)
• Neural Implicit Dense Semantic SLAM [83.04331351572277]
  We propose a novel RGBD vSLAM algorithm that learns a memory-efficient, dense 3D geometry, and semantic segmentation of an indoor scene in an online manner. Our pipeline combines classical 3D vision-based tracking and loop closing with neural fields-based mapping. Our proposed algorithm can greatly enhance scene perception and assist with a range of robot control problems.
  arXiv  Detail & Related papers  (2023-04-27T23:03:52Z)
• Graph Attention Network for Camera Relocalization on Dynamic Scenes [1.0398909602421018]
  We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment. Our approach significantly improves the camera pose accuracy of the state-of-the-art method from $0.358$ to $0.506$ on the RIO10 benchmark for dynamic indoor camera relocalization.
  arXiv  Detail & Related papers  (2022-09-29T18:57:52Z)
• MeshLoc: Mesh-Based Visual Localization [54.731309449883284]
  We explore a more flexible alternative based on dense 3D meshes that does not require features matching between database images to build the scene representation. Surprisingly competitive results can be obtained when extracting features on renderings of these meshes, without any neural rendering stage. Our results show that dense 3D model-based representations are a promising alternative to existing representations and point to interesting and challenging directions for future research.
  arXiv  Detail & Related papers  (2022-07-21T21:21:10Z)
• Vision Transformer for NeRF-Based View Synthesis from a Single Input Image [49.956005709863355]
  We propose to leverage both the global and local features to form an expressive 3D representation. To synthesize a novel view, we train a multilayer perceptron (MLP) network conditioned on the learned 3D representation to perform volume rendering. Our method can render novel views from only a single input image and generalize across multiple object categories using a single model.
  arXiv  Detail & Related papers  (2022-07-12T17:52:04Z)
• Progressive Coordinate Transforms for Monocular 3D Object Detection [52.00071336733109]
  We propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations. In this paper, we propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations.
  arXiv  Detail & Related papers  (2021-08-12T15:22:33Z)
• VS-Net: Voting with Segmentation for Visual Localization [72.8165619061249]
  We propose a novel visual localization framework that establishes 2D-to-3D correspondences between the query image and the 3D map with a series of learnable scene-specific landmarks. Our proposed VS-Net is extensively tested on multiple public benchmarks and can outperform state-of-the-art visual localization methods.
  arXiv  Detail & Related papers  (2021-05-23T08:44:11Z)
• Learning Camera Localization via Dense Scene Matching [45.0957383562443]
  Camera localization aims to estimate 6 DoF camera poses from RGB images. Recent learning-based approaches encode structures into a specific convolutional neural network (CNN) We present a new method for camera localization using dense matching (DSM)
  arXiv  Detail & Related papers  (2021-03-31T03:47:42Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.