Beyond SurfaceStatistics: Scene Representations in a Latent Diffusion Model
Stable Diffusion secretly learns 3D geometry, even without any depth data
parent: domain
Score-based Diffusion Models in Function Spacefunction diffusion (maybe audio)
Diffusion GenerativeModels in InfiniteDimensions
Manifold DiffusionFields (from texture context)
Seeing throughthe Brain: Image Reconstruction of Visual Perception from Human Brain Signals
stimuli reconstruction by reconstructing the observed images
NeuralNetwork Diffusion
utilizing an autoencoder to extracts latent representations of a subset of the network parameters
then trained to synthesize these
improved performance over trained networks