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 51–75 of 304 papers

TitleStatusHype
Back to the Feature: Learning Robust Camera Localization from Pixels to PoseCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
CaSPR: Learning Canonical Spatiotemporal Point Cloud RepresentationsCode1
LoFTR: Detector-Free Local Feature Matching with TransformersCode1
ManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan FramesCode1
Level-S^2fM: Structure from Motion on Neural Level Set of Implicit SurfacesCode1
BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric ReasoningCode1
Princeton365: A Diverse Dataset with Accurate Camera PoseCode1
E2NeRF: Event Enhanced Neural Radiance Fields from Blurry ImagesCode1
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor ExtractionCode1
Learning to Filter Outlier Edges in Global SfMCode1
Human Mesh Recovery from Arbitrary Multi-view ImagesCode1
iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse ViewsCode1
HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D ReconstructionCode1
GS-EVT: Cross-Modal Event Camera Tracking based on Gaussian SplattingCode1
How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D LinesCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Few-View Object Reconstruction with Unknown Categories and Camera PosesCode1
EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth RegistrationCode1
AirDOS: Dynamic SLAM benefits from Articulated ObjectsCode1
Extreme Two-View Geometry From Object Poses with Diffusion ModelsCode1
RePoseD: Efficient Relative Pose Estimation With Known Depth InformationCode1
Height and Uprightness Invariance for 3D Prediction From a Single ViewCode1
DFNet: Enhance Absolute Pose Regression with Direct Feature MatchingCode1
DepthMOT: Depth Cues Lead to a Strong Multi-Object TrackerCode1
Show:102550
← PrevPage 3 of 13Next →

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