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 1–25 of 304 papers

TitleStatusHype
π^3: Scalable Permutation-Equivariant Visual Geometry Learning—0
BRUM: Robust 3D Vehicle Reconstruction from 360 Sparse Images—0
SpatialTrackerV2: 3D Point Tracking Made EasyCode4
SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting RepresentationCode0
Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures—0
RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories—0
Princeton365: A Diverse Dataset with Accurate Camera PoseCode1
Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation—0
4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians—0
Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated VideosCode2
PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth—0
T-Graph: Enhancing Sparse-view Camera Pose Estimation by Pairwise Translation Graph—0
Large-scale visual SLAM for in-the-wild videos—0
SmallGS: Gaussian Splatting-based Camera Pose Estimation for Small-Baseline Videos—0
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMsCode2
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction—0
Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction—0
Regist3R: Incremental Registration with Stereo Foundation Model—0
A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds—0
Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video—0
LiM-Loc: Visual Localization with Dense and Accurate 3D Reference Maps Directly Corresponding 2D Keypoints to 3D LiDAR Point Clouds—0
Easi3R: Estimating Disentangled Motion from DUSt3R Without TrainingCode4
GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusion—0
STAMICS: Splat, Track And Map with Integrated Consistency and Semantics for Dense RGB-D SLAM—0
Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single VideoCode3
Show:102550
← PrevPage 1 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