Image Generators with Conditionally-Independent Pixel Synthesis
This work addresses the problem of efficient and flexible image synthesis for researchers and practitioners by proposing a novel architecture that removes the reliance on spatial convolutions.
This paper introduces a new image generator architecture that synthesizes each pixel's color value independently, conditioned on a latent vector and pixel coordinates. Despite lacking spatial convolutions, the new generators achieve generation quality comparable to state-of-the-art convolutional generators.
Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner. Here, we present a new architecture for image generators, where the color value at each pixel is computed independently given the value of a random latent vector and the coordinate of that pixel. No spatial convolutions or similar operations that propagate information across pixels are involved during the synthesis. We analyze the modeling capabilities of such generators when trained in an adversarial fashion, and observe the new generators to achieve similar generation quality to state-of-the-art convolutional generators. We also investigate several interesting properties unique to the new architecture.