SOTAVerified

Camera Pose Estimation

Camera pose estimation is a crucial task in computer vision and robotics that involves determining the position and orientation (pose) of a camera relative to a given reference frame. This task is essential for various applications, such as augmented reality, 3D reconstruction, SLAM, and autonomous navigation.

Papers

Showing 201250 of 304 papers

TitleStatusHype
Learnable Motion Coherence for Correspondence Pruning0
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares0
Learning Multi-View Camera Relocalization With Graph Neural Networks0
Learning Probabilistic Coordinate Fields for Robust Correspondences0
Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images0
Learning Rotation-Equivariant Features for Visual Correspondence0
Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing0
LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives0
Level Set-Based Camera Pose Estimation From Multiple 2D/3D Ellipse-Ellipsoid Correspondences0
Light3R-SfM: Towards Feed-forward Structure-from-Motion0
LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds0
Line-based Camera Pose Estimation in Point Cloud of Structured Environments0
Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization0
Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization0
Long-term 3D Localization and Pose from Semantic Labellings0
MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile AR0
Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction0
Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras0
MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose0
Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression0
RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges0
S3LAM: Structured Scene SLAM0
Sampling Based Scene-Space Video Processing0
Scalable Structure From Motion for Densely Sampled Videos0
Scaling 4D Representations0
SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?0
SCENES: Subpixel Correspondence Estimation With Epipolar Supervision0
Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos0
SHAPE: Linear-Time Camera Pose Estimation With Quadratic Error-Decay0
SiLK: Simple Learned Keypoints0
Simultaneous Super-Resolution of Depth and Images Using a Single Camera0
Single Image Camera Calibration With Lenticular Arrays for Augmented Reality0
Single-image camera calibration with model-free distortion correction0
SmallGS: Gaussian Splatting-based Camera Pose Estimation for Small-Baseline Videos0
Sparse Optical Flow-Based Line Feature Tracking0
SparsePose: Sparse-View Camera Pose Regression and Refinement0
Spatial Correspondence With Generative Adversarial Network: Learning Depth From Monocular Videos0
SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM0
STAMICS: Splat, Track And Map with Integrated Consistency and Semantics for Dense RGB-D SLAM0
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos0
SuperGF: Unifying Local and Global Features for Visual Localization0
T-Graph: Enhancing Sparse-view Camera Pose Estimation by Pairwise Translation Graph0
The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation0
Toon3D: Seeing Cartoons from New Perspectives0
Towards Design and Development of an ArUco Markers-Based Quantitative Surface Tactile Sensor0
Towards the Application of Linear Programming Methods For Multi-Camera Pose Estimation0
TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation0
TRPLP - Trifocal Relative Pose From Lines at Points0
Uncertainty-Aware Camera Pose Estimation from Points and Lines0
Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis0
Show:102550
← PrevPage 5 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Monodepth2Average Translational Error et[%]43.21Unverified
2SfMLearnerAverage Translational Error et[%]29.78Unverified
3GeoNetAverage Translational Error et[%]26.31Unverified
4SC-DepthAverage Translational Error et[%]12.2Unverified
5DeepMatchVOAverage Translational Error et[%]11.05Unverified
6SCIPaDAverage Translational Error et[%]8.63Unverified
7Manydepth2Average Translational Error et[%]7.15Unverified