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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 304 papers

TitleStatusHype
AEPnP: A Less-constrained EPnP Solver for Pose Estimation with Anisotropic ScalingCode0
Towards Design and Development of an ArUco Markers-Based Quantitative Surface Tactile Sensor—0
USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance FieldsCode1
DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance FieldsCode1
PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose EstimationCode1
Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View TransformerCode1
EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023Code0
ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models—0
PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle AdjustmentCode2
LightGlue: Local Feature Matching at Light SpeedCode4
Learning Probabilistic Coordinate Fields for Robust Correspondences—0
Two-View Geometry Scoring Without CorrespondencesCode1
FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow—0
RoMa: Robust Dense Feature MatchingCode3
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares—0
Edge-aware Consistent Stereo Video Depth Estimation—0
Region contrastive camera localizationCode0
Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation—0
Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motionCode0
Learning How To Robustly Estimate Camera Pose in Endoscopic VideosCode1
SiLK -- Simple Learned KeypointsCode2
Accelerating Globally Optimal Consensus Maximization in Geometric Vision—0
Event-based Camera Tracker by t NeRF—0
Learning Rotation-Equivariant Features for Visual Correspondence—0
DIME-Net: Neural Network-Based Dynamic Intrinsic Parameter Rectification for Cameras with Optical Image Stabilization System—0
Render-and-Compare: Cross-View 6 DoF Localization from Noisy PriorCode0
E2NeRF: Event Enhanced Neural Radiance Fields from Blurry ImagesCode1
SiLK: Simple Learned Keypoints—0
Multi-body Depth and Camera Pose Estimation from Multiple ViewsCode0
SuperGF: Unifying Local and Global Features for Visual Localization—0
Few-View Object Reconstruction with Unknown Categories and Camera PosesCode1
NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D ReconstructionCode1
SparsePose: Sparse-View Camera Pose Regression and Refinement—0
SliceMatch: Geometry-guided Aggregation for Cross-View Pose EstimationCode1
Level-S^2fM: Structure from Motion on Neural Level Set of Implicit SurfacesCode1
A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective—0
Estimating more camera poses for ego-centric videos is essential for VQ3D—0
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View CompletionCode2
MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose—0
Robustifying the Multi-Scale Representation of Neural Radiance Fields—0
CoVisPose: Co-Visibility Pose Transformer for Wide-Baseline Relative Pose Estimation in 360◦ Indoor Panoramas—0
Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences—0
Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence—0
PRIF: Primary Ray-based Implicit Function—0
MeshLoc: Mesh-Based Visual LocalizationCode2
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the WildCode2
Level Set-Based Camera Pose Estimation From Multiple 2D/3D Ellipse-Ellipsoid Correspondences—0
PVO: Panoptic Visual OdometryCode2
Improving Worst Case Visual Localization Coverage via Place-specific Sub-selection in Multi-camera Systems—0
HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D ReconstructionCode1
Show:102550
← PrevPage 3 of 7Next →

Benchmark Results

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