InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
Paper
•
2309.03895
•
Published
•
13
Diffusion Model
-
-
ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
Paper • 2309.16650 • Published • 10 -
CCEdit: Creative and Controllable Video Editing via Diffusion Models
Paper • 2309.16496 • Published • 9 -
FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling
Paper • 2310.15169 • Published • 9 -
Wonder3D: Single Image to 3D using Cross-Domain Diffusion
Paper • 2310.15008 • Published • 21 -
Matryoshka Diffusion Models
Paper • 2310.15111 • Published • 40 -
TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
Paper • 2310.13772 • Published • 6 -
HyperFields: Towards Zero-Shot Generation of NeRFs from Text
Paper • 2310.17075 • Published • 14 -
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
Paper • 2310.17359 • Published • 1 -
CodeFusion: A Pre-trained Diffusion Model for Code Generation
Paper • 2310.17680 • Published • 69 -
CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models
Paper • 2310.19784 • Published • 9 -
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
Paper • 2310.20700 • Published • 9 -
Beyond U: Making Diffusion Models Faster & Lighter
Paper • 2310.20092 • Published • 11 -
Controllable Music Production with Diffusion Models and Guidance Gradients
Paper • 2311.00613 • Published • 24 -
De-Diffusion Makes Text a Strong Cross-Modal Interface
Paper • 2311.00618 • Published • 21 -
E3 TTS: Easy End-to-End Diffusion-based Text to Speech
Paper • 2311.00945 • Published • 14 -
The Chosen One: Consistent Characters in Text-to-Image Diffusion Models
Paper • 2311.10093 • Published • 57 -
UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs
Paper • 2311.09257 • Published • 45 -
MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer
Paper • 2311.12052 • Published • 32 -
Diffusion Model Alignment Using Direct Preference Optimization
Paper • 2311.12908 • Published • 47 -
AnimateZero: Video Diffusion Models are Zero-Shot Image Animators
Paper • 2312.03793 • Published • 17 -
Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis
Paper • 2312.03491 • Published • 34 -
StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation
Paper • 2312.12491 • Published • 69 -
Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model
Paper • 2312.13252 • Published • 27 -
InstructVideo: Instructing Video Diffusion Models with Human Feedback
Paper • 2312.12490 • Published • 17 -
DREAM-Talk: Diffusion-based Realistic Emotional Audio-driven Method for Single Image Talking Face Generation
Paper • 2312.13578 • Published • 27 -
AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
Paper • 2402.00769 • Published • 20 -
Magic-Me: Identity-Specific Video Customized Diffusion
Paper • 2402.09368 • Published • 27 -
MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models
Paper • 2402.06178 • Published • 13 -
FiT: Flexible Vision Transformer for Diffusion Model
Paper • 2402.12376 • Published • 48 -
Music Style Transfer with Time-Varying Inversion of Diffusion Models
Paper • 2402.13763 • Published • 10 -
EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
Paper • 2402.17485 • Published • 189 -
Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners
Paper • 2402.17723 • Published • 16 -
Scalable Diffusion Models with Transformers
Paper • 2212.09748 • Published • 16 -
3D Diffusion Policy
Paper • 2403.03954 • Published • 11 -
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
Paper • 2403.05135 • Published • 42 -
StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control
Paper • 2403.09055 • Published • 24
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
Paper • 2406.08659 • Published • 8Note 研究者採用了擴散模型，將T2MVid生成問題分解為視角空間和時間組件，並利用預訓練的多視角圖像和2D視頻擴散模型層來確保視頻的多視角一致性和時間連續性。引入對齊模塊解決了由於2D和多視角數據之間的領域差異引起的層不兼容問題。此外，還貢獻了一個新的多視角視頻數據集。
GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors
Paper • 2406.10111 • Published • 6Note 本文提出的GaussianSR方法通過引入2D生成先驗，並通過減少隨機性干擾來優化3DGS，成功實現了高品質的HRNVS，顯著超越了現有的最先進方法。這項研究為高解析度視角合成提供了一個新思路，具有重要的應用價值。
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
Paper • 2406.09416 • Published • 28Note 本文提出的DiMR和TD-LN方法有效地平衡了影像細節捕捉與計算複雜度，顯著減少了影像失真，並在ImageNet生成基準測試中展示出卓越的性能，為高保真影像生成設定了新的標杆。
AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation
Paper • 2406.07686 • Published • 14Note AV-DiT展示了一種高效的音視擴散變壓器架構，通過利用預訓練的圖像生成變壓器並進行輕量級的適配，實現了高質量的音視頻聯合生成。這不僅填補了現有方法的空白，還展示了多模態生成在降低計算成本和模型複雜度方面的潛力。
-
Repulsive Score Distillation for Diverse Sampling of Diffusion Models
Paper • 2406.16683 • Published • 4 -
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Paper • 2407.01392 • Published • 39 -
Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization
Paper • 2308.09716 • Published • 2 -
Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model
Paper • 2407.16982 • Published • 40 -
Diffusion Feedback Helps CLIP See Better
Paper • 2407.20171 • Published • 35 -
DC3DO: Diffusion Classifier for 3D Objects
Paper • 2408.06693 • Published • 10 -
3D Gaussian Editing with A Single Image
Paper • 2408.07540 • Published • 10 -
TurboEdit: Instant text-based image editing
Paper • 2408.08332 • Published • 19