Insights on Evaluation of Camera Re-localization Using Relative Pose Regression

• URL: http://arxiv.org/abs/2009.11342v1
• Date: Wed, 23 Sep 2020 19:16:26 GMT
• Title: Insights on Evaluation of Camera Re-localization Using Relative Pose Regression
• Authors: Amir Shalev (1,2), Omer Achrack (2), Brian Fulkerson, and Ben-Zion Bobrovsky (1) ((1) Tel-Aviv-University, (2) Intel)
• Abstract summary: We consider the problem of relative pose regression in visual relocalization. We propose three new metrics to remedy the issue mentioned above. We show that our network generalizes well, specifically, training on a single scene leads to little loss of performance on the other scenes.
• Score: 0.9236074230806579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the problem of relative pose regression in visual relocalization. Recently, several promising approaches have emerged in this area. We claim that even though they demonstrate on the same datasets using the same split to train and test, a faithful comparison between them was not available since on currently used evaluation metric, some approaches might perform favorably, while in reality performing worse. We reveal a tradeoff between accuracy and the 3D volume of the regressed subspace. We believe that unlike other relocalization approaches, in the case of relative pose regression, the regressed subspace 3D volume is less dependent on the scene and more affect by the method used to score the overlap, which determined how closely sampled viewpoints are. We propose three new metrics to remedy the issue mentioned above. The proposed metrics incorporate statistics about the regression subspace volume. We also propose a new pose regression network that serves as a new baseline for this task. We compare the performance of our trained model on Microsoft 7-Scenes and Cambridge Landmarks datasets both with the standard metrics and the newly proposed metrics and adjust the overlap score to reveal the tradeoff between the subspace and performance. The results show that the proposed metrics are more robust to different overlap threshold than the conventional approaches. Finally, we show that our network generalizes well, specifically, training on a single scene leads to little loss of performance on the other scenes.

Related papers

• DOR3D-Net: Dense Ordinal Regression Network for 3D Hand Pose Estimation [6.327974053228352]
  We re-formulate 3D hand pose estimation as a dense ordinal regression problem. We propose a novel Dense Ordinal Regression 3D Pose Network (DOR3D-Net) Our design provides significant improvements over SOTA methods.
  arXiv  Detail & Related papers  (2024-03-20T08:47:51Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Consensus-Adaptive RANSAC [104.87576373187426]
  We propose a new RANSAC framework that learns to explore the parameter space by considering the residuals seen so far via a novel attention layer. The attention mechanism operates on a batch of point-to-model residuals, and updates a per-point estimation state to take into account the consensus found through a lightweight one-step transformer.
  arXiv  Detail & Related papers  (2023-07-26T08:25:46Z)
• LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference [66.45326873274908]
  We propose a novel method, LoLep, which regresses Locally-Learned planes from a single RGB image to represent scenes accurately. Compared to MINE, our approach has an LPIPS reduction of 4.8%-9.0% and an RV reduction of 73.9%-83.5%.
  arXiv  Detail & Related papers  (2023-07-23T03:38:55Z)
• Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking [66.83273589348758]
  Link prediction attempts to predict whether an unseen edge exists based on only a portion of edges of a graph. A flurry of methods have been introduced in recent years that attempt to make use of graph neural networks (GNNs) for this task. New and diverse datasets have also been created to better evaluate the effectiveness of these new models.
  arXiv  Detail & Related papers  (2023-06-18T01:58:59Z)
• RELMOBNET: A Robust Two-Stage End-To-End Training Approach For MOBILENETV3 Based Relative Camera Pose Estimation [0.6193838300896449]
  Relative camera pose estimation plays a pivotal role in dealing with 3D reconstruction and visual localization. We propose a Siamese network based on MobileNetV3-Large for an end-to-end relative camera pose regression independent of camera parameters.
  arXiv  Detail & Related papers  (2022-02-25T17:27:26Z)
• LENS: Localization enhanced by NeRF synthesis [3.4386226615580107]
  We demonstrate improvement of camera pose regression thanks to an additional synthetic dataset rendered by the NeRF class of algorithm. We further improved localization accuracy of pose regressors using synthesized realistic and geometry consistent images as data augmentation during training.
  arXiv  Detail & Related papers  (2021-10-13T08:15:08Z)
• Reassessing the Limitations of CNN Methods for Camera Pose Regression [27.86655424544118]
  We propose a model that can directly regress the camera pose from images with significantly higher accuracy than existing methods of the same class. We first analyse why regression methods are still behind the state-of-the-art, and we bridge the performance gap with our new approach.
  arXiv  Detail & Related papers  (2021-08-16T17:55:26Z)
• Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression [81.05772887221333]
  We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. We present a simple yet effective approach, named disentangled keypoint regression (DEKR) We empirically show that the proposed direct regression method outperforms keypoint detection and grouping methods.
  arXiv  Detail & Related papers  (2021-04-06T05:54:46Z)
• Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes [56.27436157101251]
  We propose a novel approach to learn human mesh reconstruction without any ground truth meshes. This is made possible by introducing two new terms into the loss function of a graph convolutional neural network (Graph CNN)
  arXiv  Detail & Related papers  (2020-02-28T20:30:07Z)

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.