Stochastic Conditional Diffusion Models for Semantic Image Synthesis
CoRR(2024)
摘要
Semantic image synthesis (SIS) is a task to generate realistic images
corresponding to semantic maps (labels). It can be applied to diverse
real-world practices such as photo editing or content creation. However, in
real-world applications, SIS often encounters noisy user inputs. To address
this, we propose Stochastic Conditional Diffusion Model (SCDM), which is a
robust conditional diffusion model that features novel forward and generation
processes tailored for SIS with noisy labels. It enhances robustness by
stochastically perturbing the semantic label maps through Label Diffusion,
which diffuses the labels with discrete diffusion. Through the diffusion of
labels, the noisy and clean semantic maps become similar as the timestep
increases, eventually becoming identical at t=T. This facilitates the
generation of an image close to a clean image, enabling robust generation.
Furthermore, we propose a class-wise noise schedule to differentially diffuse
the labels depending on the class. We demonstrate that the proposed method
generates high-quality samples through extensive experiments and analyses on
benchmark datasets, including a novel experimental setup simulating human
errors during real-world applications.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要