Subspace Diffusion Generative Models
Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimensionality and incur all the inconveniences thereof. Instead, we restrict the diffusion via projections onto subspaces as the data distribution evolves toward noise. When applied to state-of-the-art models, our framework simultaneously improves sample quality -- reaching an FID of 2.17 on unconditional CIFAR-10 -- and reduces the computational cost of inference for the same number of denoising steps. Our framework is fully compatible with continuous-time diffusion and retains its flexible capabilities, including exact log-likelihoods and controllable generation. Code is available at https://github.com/bjing2016/subspace-diffusion.
Code (1)
Tasks
DenoisingImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Diffusion Subspace Clustering for Hyperspectral Images
Hyperspectral image (HSI) subspace clustering remains a challenging task due to the poor spatial and rich spectral resolutions of HSIs. Most of the existing HSI subspace clustering approaches just extract the spatial and…
ClusteringMoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex …
NullFlow: One-Step Generative Reconstruction
We propose NullFlow, a principled framework for one-step generative image reconstruction. Our key idea is to confine the generative flow to a measurement-consistent subspace. Because the flow never leaves this subspace, …
Image ReconstructionImage InpaintingLosing dimensions: Geometric memorization in generative diffusion
Generative diffusion processes are state-of-the-art machine learning models deeply connected with fundamental concepts in statistical physics. Depending on the dataset size and the capacity of the network, their behavior…
MemorizationDiffscaler: Enhancing the Generative Prowess of Diffusion Transformers
Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-ba…
Image GenerationUnconditional Image Generation