Papers with Code 아카이브
3D Human Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 9
- 평가표
- 25
- 보존된 평가 기록
- 447
3D Human Pose Estimation is a computer vision task that involves estimating the 3D positions and orientations of body joints and bones from 2D images or videos. The goal is to reconstruct the 3D pose of a person in real-time, which can be used in a variety of applications, such as virtual reality, human-computer interaction, and motion analysis.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
2L3: Lifting Imperfect Generated 2D Images into Accurate 3D
Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras
Towards a large-scale fused and labeled dataset of human pose while interacting with robots in shared urban areas
SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Cameras
DeepRLI: A Multi-objective Framework for Universal Protein--Ligand Interaction Prediction
Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework
Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution
Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video
Collaboratively Self-supervised Video Representation Learning for Action Recognition
Deep Blind Super-Resolution for Satellite Video
Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton
FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring
D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement
AGG: Amortized Generative 3D Gaussians for Single Image to 3D
STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion
GD^2-NeRF: Generative Detail Compensation via GAN and Diffusion for One-shot Generalizable Neural Radiance Fields
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
3D Human Pose Perception from Egocentric Stereo Videos
Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstruction
A Survey on Super Resolution for video Enhancement Using GAN
HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D
Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation
ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation
Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks
STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimation
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
3D-LFM: Lifting Foundation Model
TMP: Temporal Motion Propagation for Online Video Super-Resolution
SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentation
Customize-It-3D: High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior
Semantic Lens: Instance-Centric Semantic Alignment for Video Super-Resolution
FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.