Papers with Code 아카이브
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Light3R-SfM: Towards Feed-forward Structure-from-Motion
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
RePoseD: Efficient Relative Pose Estimation With Known Depth Information
JOG3R: Towards 3D-Consistent Video Generators
KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences
Reconstructing People, Places, and Cameras
Scaling 4D Representations
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Information
MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers
One Diffusion to Generate Them All
SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild
USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
Activating Self-Attention for Multi-Scene Absolute Pose Regression
Robust Two-View Geometry Estimation with Implicit Differentiation
Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization
Enhancing Soccer Camera Calibration Through Keypoint Exploitation
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
PuzzleBoard: A New Camera Calibration Pattern with Position Encoding
GS-EVT: Cross-Modal Event Camera Tracking based on Gaussian Splatting
Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS
ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation
Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis
E$^3$NeRF: Efficient Event-Enhanced Neural Radiance Fields from Blurry Images
DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction
RADA: Robust and Accurate Feature Learning with Domain Adaptation
Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localization
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning
MVSBoost: An Efficient Point Cloud-based 3D Reconstruction
GLACE: Global Local Accelerated Coordinate Encoding
Intensity and Texture Correction of Omnidirectional Image Using Camera Images for Indirect Augmented Reality
Toon3D: Seeing Cartoons from New Perspectives
GISR: Geometric Initialization and Silhouette-based Refinement for Single-View Robot Pose and Configuration Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.