Research map / Image generation / Autoregressive and latent generation
PixelNN: Example-based Image Synthesis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use oracle selection rather than a random single output | PixelNN · Normals-to-RGB, Human Faces | AP: 0.38 -> 0.42 | Helped |
| Use oracle selection rather than a random single output | PixelNN · Normals-to-RGB, Cats and Dogs | AP: 0.80 -> 0.92 | Helped |
| Use oracle selection rather than a random single output | PixelNN · Edges-to-RGB, Human Faces | AP: 0.38 -> 0.41 | Helped |
| Use oracle selection rather than a random single output | PixelNN · Edges-to-RGB, Cats and Dogs | AP: 0.77 -> 0.89 | Helped |
| Use PixelNN with oracle output selection instead of Pix-to-Pix with oracle selection | PixelNN · Normals-to-RGB, Human Faces | AP: 0.34 -> 0.42 | Helped |
| Use PixelNN with oracle output selection instead of Pix-to-Pix with oracle selection | PixelNN · Normals-to-RGB, Cats and Dogs | AP: 0.85 -> 0.92 | Helped |
| Use PixelNN with oracle output selection instead of Pix-to-Pix with oracle selection | PixelNN · Edges-to-RGB, Human Faces | AP: 0.35 -> 0.41 | Helped |
| Use PixelNN with oracle output selection instead of Pix-to-Pix with oracle selection | PixelNN · Edges-to-RGB, Cats and Dogs | AP: 0.81 -> 0.89 | Helped |
| Use PixelNN with random single-output selection instead of Pix-to-Pix | PixelNN · Normals-to-RGB, Cats and Dogs | AP: 0.82 -> 0.80 | Hurt |
| Use PixelNN with random single-output selection instead of Pix-to-Pix | PixelNN · Edges-to-RGB, Cats and Dogs | AP: 0.78 -> 0.77 | Hurt |
Closest papers by meaning
- Conditional Image Generation with PixelCNN Decoders (NeurIPS 2016 · similarity 0.89)
- Spatially-Adaptive Pixelwise Networks for Fast Image Translation (CVPR 2021 · similarity 0.88)
- PixelCNN Models with Auxiliary Variables for Natural Image Modeling (ICML 2017 · similarity 0.88)
- Large Scale GAN Training for High Fidelity Natural Image Synthesis (ICLR 2019 · similarity 0.88)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (CVPR 2024 · similarity 0.87)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.