https://github.com/i2-multimedia-lab/diffusest
공식 코드DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer
Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution
NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction
PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation
Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Effective Whole-body Pose Estimation with Two-stages Distillation
Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation
Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning Approaches
StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning
Zero Shot Audio to Audio Emotion Transfer With Speaker Disentanglement
Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation
PoserNet: Refining Relative Camera Poses Exploiting Object Detections
VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
Active Transfer Learning for Efficient Video-Specific Human Pose Estimation
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches
Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation
InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation
InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.