https://github.com/ylabbe/cosypose
CosyPose: Consistent multi-view multi-object 6D pose estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
CosyPose: Consistent multi-view multi-object 6D pose estimation
WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
Unsupervised learning of object semantic parts from internal states of CNNs by population encoding
DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation
iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching
High-Resolution Representations for Labeling Pixels and Regions
Semantic keypoint-based pose estimation from single RGB frames
LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation
StyleBank: An Explicit Representation for Neural Image Style Transfer
Deep High-Resolution Representation Learning for Visual Recognition
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation
Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.