classifier-as-generator.github.io - Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

home > domains > classifier-as-generator.github.io

Description: Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

nerf (195) d-nerf (90) nerfies (89)

Example domain paragraphs

Classifiers and generators have long been separated. We break down this separation and showcase that conventional neural network classifiers can generate high-quality images of a large number of categories, being comparable to the state-of-the-art generative models (e.g., DDPMs and GANs). We achieve this by computing the partial derivative of the classification loss function with respect to the input to optimize the input to produce an image. Since it is widely known that directly optimizing the inputs is s

Goodfellow et al., Generative adversarial networks, 2014.

StyleLight: HDR Panorama Generation for Lighting Estimation and Editing, 2022.

Links to classifier-as-generator.github.io (4)

• sparsenerf.github.io SparseNeRF
• style-light.github.io StyleLight: HDR Panorama Generation for Lighting Estimation and Editing
• wanggrun.github.io Guangrun Wang (王广润)'s Homepage
• perf-project.github.io PERF