Camera Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 7
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Chenyu-Wang567/All-Angles-Bench
공식 코드Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
https://github.com/Davidyao99/uni4d
공식 코드Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
https://github.com/EasonChen99/EVLoc
공식 코드EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration
https://github.com/HKUST-Aerial-Robotics/ESVO
공식 코드https://github.com/HSarham/automatic-ar
공식 코드Simultaneous Multi-View Camera Pose Estimation and Object Tracking with Square Planar Markers
https://github.com/JiawangBian/sc_depth_pl
공식 코드Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
https://github.com/KU-CVLAB/CoPoNeRF
공식 코드Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs
https://github.com/NVlabs/CF-3DGS
공식 코드https://github.com/NikolasEnt/soccernet-calibration-sportlight
공식 코드Enhancing Soccer Camera Calibration Through Keypoint Exploitation
https://github.com/PStelldinger/PuzzleBoard
공식 코드PuzzleBoard: A New Camera Calibration Pattern with Position Encoding
https://github.com/Shiaoming/ALIKE
공식 코드ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
https://github.com/Totoro97/Vid2Curve
공식 코드Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video
https://github.com/WU-CVGL/USB-NeRF
공식 코드USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
https://github.com/activevisionlab/dfnet
공식 코드DFNet: Enhance Absolute Pose Regression with Direct Feature Matching
https://github.com/aimi-lab/robust-pose-estimator
공식 코드Learning How To Robustly Estimate Camera Pose in Endoscopic Videos
https://github.com/amir32002/3D_Street_View
공식 코드https://github.com/anitarau/simcol
공식 코드https://github.com/arthurchen0518/DirectionNet
공식 코드Wide-Baseline Relative Camera Pose Estimation with Directional Learning
https://github.com/axelbarroso/scalenet
공식 코드https://github.com/bcv-uniandes/egocol
공식 코드https://github.com/bluedream1121/REKD
공식 코드Self-Supervised Equivariant Learning for Oriented Keypoint Detection
https://github.com/bluedream1121/self-sca-ori
공식 코드https://github.com/bytedance/particle-sfm
공식 코드ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild
https://github.com/chenkang455/usp-gaussian
공식 코드USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
https://github.com/chinhsuanwu/ifusion
공식 코드iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
https://github.com/choyaa/render2loc
공식 코드Render-and-Compare: Cross-View 6 DoF Localization from Noisy Prior
https://github.com/cvg/glace
공식 코드https://github.com/cvg/lightglue
공식 코드https://github.com/cvg/pixloc
공식 코드Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
https://github.com/daizhirui/bevnet
공식 코드BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning
https://github.com/davrempe/caspr
공식 코드CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
https://github.com/dlalth557/ActMST
공식 코드Activating Self-Attention for Multi-Scene Absolute Pose Regression
https://github.com/dwawayu/pensieve
공식 코드Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos
https://github.com/ensv/RPNet
공식 코드RPNet: an End-to-End Network for Relative Camera Pose Estimation
https://github.com/eric-yyjau/pytorch-deepFEPE
공식 코드Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.