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 51100 of 304 papers

TitleStatusHype
Back to the Feature: Learning Robust Camera Localization from Pixels to PoseCode1
Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB VideoCode1
Towards Accurate Active Camera LocalizationCode1
Extreme Two-View Geometry From Object Poses with Diffusion ModelsCode1
Self-supervised Geometric PerceptionCode1
Self-Supervised Equivariant Learning for Oriented Keypoint DetectionCode1
Self-Supervised Learning of Image Scale and OrientationCode1
ScaleNet: A Shallow Architecture for Scale EstimationCode1
CaSPR: Learning Canonical Spatiotemporal Point Cloud RepresentationsCode1
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint LearningCode1
PuzzleBoard: A New Camera Calibration Pattern with Position EncodingCode1
Wide-Baseline Relative Camera Pose Estimation with Directional LearningCode1
PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose EstimationCode1
PoGO-Net: Pose Graph Optimization With Graph Neural NetworksCode1
P1AC: Revisiting Absolute Pose From a Single Affine CorrespondenceCode1
RePoseD: Efficient Relative Pose Estimation With Known Depth InformationCode1
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor ExtractionCode1
Neural Reprojection Error: Merging Feature Learning and Camera Pose EstimationCode1
E2NeRF: Event Enhanced Neural Radiance Fields from Blurry ImagesCode1
ManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan FramesCode1
Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic ScenesCode1
Level-S^2fM: Structure from Motion on Neural Level Set of Implicit SurfacesCode1
Learning to Filter Outlier Edges in Global SfMCode1
Learning How To Robustly Estimate Camera Pose in Endoscopic VideosCode1
LoFTR: Detector-Free Local Feature Matching with TransformersCode1
DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance FieldsCode1
Human Mesh Recovery from Arbitrary Multi-view ImagesCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D ReconstructionCode1
AirDOS: Dynamic SLAM benefits from Articulated ObjectsCode1
NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D ReconstructionCode1
How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D LinesCode1
iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse ViewsCode1
DFNet: Enhance Absolute Pose Regression with Direct Feature MatchingCode1
DepthMOT: Depth Cues Lead to a Strong Multi-Object TrackerCode1
Princeton365: A Diverse Dataset with Accurate Camera PoseCode1
Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View TransformerCode1
Few-View Object Reconstruction with Unknown Categories and Camera PosesCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Bimodal Camera Pose Prediction for EndoscopyCode1
Collaborative Dense SLAMCode1
GS-EVT: Cross-Modal Event Camera Tracking based on Gaussian SplattingCode1
Height and Uprightness Invariance for 3D Prediction From a Single ViewCode1
Event-based Stereo Visual OdometryCode1
Simultaneous Multi-View Camera Pose Estimation and Object Tracking with Square Planar MarkersCode1
Adversarial Transfer of Pose Estimation Regression0
DeepMorph: A System for Hiding Bitstrings in Morphable Vector Drawings0
AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers0
Beyond Photometric Consistency: Gradient-based Dissimilarity for Improving Visual Odometry and Stereo Matching0
GISR: Geometric Initialization and Silhouette-based Refinement for Single-View Robot Pose and Configuration Estimation0
Show:102550
← PrevPage 2 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