DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations

arXiv:2401.12517v2 Announce Type: replace
Abstract: Recent studies have introduced a new class of generative models for synthesizing implicit neural representations (INRs) that capture arbitrary continuous signals in various domains. These models opened the door for domain-agnostic generative models, but they often fail to achieve high-quality generation. We observed that the existing methods generate the weights of neural networks to parameterize INRs and evaluate the network with fixed positional embeddings (PEs). Arguably, this architecture limits the expressive power of generative models …

abstract arxiv class continuous cs.lg diffusion diffusion models domain domains generative generative models implicit neural representations latent diffusion models quality stat.ml studies type