Papers with Code 아카이브
Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 17
- 평가표
- 31
- 보존된 평가 기록
- 235
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
<span style="color:grey; opacity: 0.6">( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/jimmyzou/humanposetracking_snn
공식 코드Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer
https://github.com/jimmyzou/snipper
공식 코드https://github.com/jin-s13/COCO-WholeBody
공식 코드https://github.com/jin-s13/unifs
공식 코드UniFS: Universal Few-shot Instance Perception with Point Representations
https://github.com/jingyunliang/hcflow
공식 코드Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
https://github.com/jingyunliang/rvrt
공식 코드Recurrent Video Restoration Transformer with Guided Deformable Attention
https://github.com/jingyunliang/swinir
공식 코드https://github.com/jingyunliang/vrt
공식 코드https://github.com/jinsuyoo/SSA-VSR
공식 코드https://github.com/jixingwu/sol-slam
공식 코드An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World
https://github.com/jiy173/MANA
공식 코드Memory-Augmented Non-Local Attention for Video Super-Resolution
https://github.com/jizhaox/relpose-6pt
공식 코드Six-Point Method for Multi-Camera Systems with Reduced Solution Space
https://github.com/jizhaox/relpose-mcs-depth
공식 코드Affine Correspondences between Multi-Camera Systems for Relative Pose Estimation
https://github.com/jjkislele/monoMotionDiff
공식 코드https://github.com/jkpark0825/eanet
공식 코드Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recovery
https://github.com/jkulhanek/viewformer
공식 코드ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers
https://github.com/jmorlana/dran
공식 코드Reuse your features: unifying retrieval and feature-metric alignment
https://github.com/jnnan/chairs
공식 코드https://github.com/johannwyh/meat
공식 코드MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
https://github.com/jonathanventura/p1ac
공식 코드P1AC: Revisiting Absolute Pose From a Single Affine Correspondence
https://github.com/joshi-bharat/deep_underwater_localization
공식 코드DeepURL: Deep Pose Estimation Framework for Underwater Relative Localization
https://github.com/jotabravo/spacecraft-tta
공식 코드Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis
https://github.com/jotabravo/spacecraft-uda
공식 코드https://github.com/jswati31/cuda-ghr
공식 코드CUDA-GHR: Controllable Unsupervised Domain Adaptation for Gaze and Head Redirection
https://github.com/junggy/housecat6d
공식 코드https://github.com/junkunyuan/hap
공식 코드HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
https://github.com/junpan19/ETDM
공식 코드Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
https://github.com/junpan19/RRN
공식 코드https://github.com/junpan19/RSDN
공식 코드Video Super-Resolution with Recurrent Structure-Detail Network
https://github.com/junpan19/VSR_TGA
공식 코드https://github.com/junshutang/3DFaceShop
공식 코드3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation
https://github.com/junwuzhang19/repaint123
공식 코드https://github.com/junyuandeng/dm-calib
공식 코드Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration
https://github.com/junzastar/dftr_voting
공식 코드https://github.com/justimyhxu/grm
공식 코드GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.