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.
HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation
EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events
Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution
Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
3D Human Pose Estimation via Spatial Graph Order Attention and Temporal Body Aware Transformer
DiMeR: Disentangled Mesh Reconstruction Model
RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution
Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms
TwoSquared: 4D Generation from 2D Image Pairs
Event-Enhanced Blurry Video Super-Resolution
ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping
Benchmarking 3D Human Pose Estimation Models Under Occlusions
Art3D: Training-Free 3D Generation from Flat-Colored Illustration
Multi-person Physics-based Pose Estimation for Combat Sports
Objaverse++: Curated 3D Object Dataset with Quality Annotations
An Empirical Study of GPT-4o Image Generation Capabilities
PromptHMR: Promptable Human Mesh Recovery
Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks
Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimation
HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation
FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video
RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond
3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models
AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction
DiffusionTalker: Efficient and Compact Speech-Driven 3D Talking Head via Personalizer-Guided Distillation
DVG-Diffusion: Dual-View Guided Diffusion Model for CT Reconstruction from X-Rays
Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation
Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes
SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution
Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses
Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation
Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.