https://github.com/spengliang/sudo
Diffusion Model Alignment Using Direct Preference Optimization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Diffusion Model Alignment Using Direct Preference Optimization
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
High-Resolution Image Synthesis with Latent Diffusion Models
MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models
Verification of Deep Convolutional Neural Networks Using ImageStars
Automatically Annotating Indoor Images with CAD Models via RGB-D Scans
Restormer: Efficient Transformer for High-Resolution Image Restoration
Associative Embedding: End-to-End Learning for Joint Detection and Grouping
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
Deep High-Resolution Representation Learning for Human Pose Estimation
VIBE: Video Inference for Human Body Pose and Shape Estimation
Instance Normalization: The Missing Ingredient for Fast Stylization
Epoch-Synchronous Overlap-Add (ESOLA) for Time- and Pitch-Scale Modification of Speech Signals
Learning Linear Transformations for Fast Arbitrary Style Transfer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.