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.
PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation
Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors
Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution
RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation
Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
VEnhancer: Generative Space-Time Enhancement for Video Generation
Controlling Space and Time with Diffusion Models
VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving
Markerless Multi-view 3D Human Pose Estimation: a survey
Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation
DaBiT: Depth and Blur informed Transformer for Joint Refocusing and Super-Resolution
Improving Generative Adversarial Networks for Video Super-Resolution
ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image
EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation
MeshPose: Unifying DensePose and 3D Body Mesh reconstruction
Generative Lifting of Multiview to 3D from Unknown Pose: Wrapping NeRF inside Diffusion
GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement
RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion
3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information
Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation
KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation
TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes
GECO: Generative Image-to-3D within a SECOnd
Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment
$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding
Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation
Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera
RemoCap: Disentangled Representation Learning for Motion Capture
Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.