https://github.com/opencalib/calibanything
공식 코드Calib-Anything: Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Camera calibration involves estimating camera parameters(including camera intrinsics and extrinsics) to infer geometric features from captured sequences, which is crucial for computer vision and robotics. Driven by different architectures of the neural network, the researchers have developed two main paradigms for learning-based camera calibration and its applications. One is Regression-based Calibration,Reconstruction-based Calibration is another.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Calib-Anything: Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything
Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve
Triplet: Triangle Patchlet for Mesh-Based Inverse Rendering and Scene Parameters Approximation
SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries
Tame a Wild Camera: In-the-Wild Monocular Camera Calibration
SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap
MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames
Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration
Automated Static Camera Calibration with Intelligent Vehicles
MARIO: Modular and Extensible Architecture for Computing Visual Statistics in RoboCup SPL
Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly using Machine Learning
PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction
Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection
BabelCalib: A Universal Approach to Calibrating Central Cameras
Infrastructure-based Multi-Camera Calibration using Radial Projections
Multi-View Masked World Models for Visual Robotic Manipulation
PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
Probabilistic Inference for Camera Calibration in Light Microscopy under Circular Motion
W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration
From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration
NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.