SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation
Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate generative distributions. This work presents a new score-decomposed diffusion model (SDDM) on manifolds to explicitly optimize the tangled distributions during image generation. SDDM derives manifolds to make the distributions of adjacent time steps separable and decompose the score function or energy guidance into an image `denoising" part and a content `refinement" part. To refine the image in the same noise level, we equalize the refinement parts of the score function and energy guidance, which permits multi-objective optimization on the manifold. We also leverage the block adaptive instance normalization module to construct manifolds with lower dimensions but still concentrated with the perturbed reference image. SDDM outperforms existing SBDM-based methods with much fewer diffusion steps on several I2I benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImage DenoisingImage GenerationImage-to-Image TranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Distributed-Memory Sparse Kernels for Machine Learning
Sampled Dense Times Dense Matrix Multiplication (SDDMM) and Sparse Times Dense Matrix Multiplication (SpMM) appear in diverse settings, such as collaborative filtering, document clustering, and graph embedding. Frequentl…
BIG-bench Machine LearningCollaborative FilteringGraph EmbeddingAutoSAGE: Input-Aware CUDA Scheduling for Sparse GNN Aggregation (SpMM/SDDMM) and CSR Attention
Sparse GNN aggregations (CSR SpMM/SDDMM) vary widely in performance with degree skew, feature width, and GPU micro-architecture. We present AutoSAGE, an input-aware CUDA scheduler that chooses tiling and mapping per inpu…
Optimal Transport-Guided Conditional Score-Based Diffusion Model
Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation. However, it requires the paired data as cond…
Optimal Transport-Guided Conditional Score-Based Diffusion Models
Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation. However, it requires the paired data as cond…
Image-to-Image TranslationSuper-ResolutionTranslationRiemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networks
Riemannian diffusion models generalize score-based generative modeling to manifold-supported data via stochastic diffusion equations on the manifold. However, training requires sampling from and differentiating the manif…
Point Clouds