https://github.com/stefp/whorl_pose_detector
공식 코드BranchPoseNet: Characterizing tree branching with a deep learning-based pose estimation approach
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
BranchPoseNet: Characterizing tree branching with a deep learning-based pose estimation approach
Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model
Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
ContactGen: Generative Contact Modeling for Grasp Generation
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation
Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects
Self-supervised Learning of Contextualized Local Visual Embeddings
Learning Affine Correspondences by Integrating Geometric Constraints
Efficient Personalized Text-to-image Generation by Leveraging Textual Subspace
Blind Image Deblurring with Unknown Kernel Size and Substantial Noise
Scalable Neural Video Representations with Learnable Positional Features
Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example
Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion
DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models
Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition
Deep Translation Prior: Test-time Training for Photorealistic Style Transfer
Correlation Matching Transformation Transformers for UHD Image Restoration
Realistic Data Generation for 6D Pose Estimation of Surgical Instruments
Talking Face Generation by Conditional Recurrent Adversarial Network
ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding
Speak Like a Dog: Human to Non-human creature Voice Conversion
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.