Research map / Probabilistic and scientific modeling / Variational and generative sampling
Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks
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 |
|---|---|---|---|
| Add local state features to constant-parameter guide (ablation) | neurally-guided vine model · Glyph shape matching | wall-clock speedup at similarity 0.35: 5.5 times | Helped |
| Add target image features (ablation) | neurally-guided model · Glyph shape matching | wall-clock speedup: 1.5 times | Helped |
| Add partial output features (All Features) (ablation) | neurally-guided model · Glyph shape matching | wall-clock speedup: 1.25 times | Helped |
| Use four-component mixtures for continuous choices (ablation) | neurally-guided model · Glyph shape matching | similarity | Helped |
| Use more than four mixture components (ablation) | neurally-guided model · Glyph shape matching | similarity | No clear effect |
| Increase number of training examples beyond ~1000 (ablation) | neurally-guided model · similarity at 10 particles | similarity: 1000 | No clear effect |
| Give unguided model equal wall-clock time instead of equal particles | Unguided · Glyph shape matching | visual quality | Mixed |
| Increase unguided particles to ~200 | Unguided · Glyph shape matching | similarity: 200 | Helped |
| Add more features to guide, at 10 particles (ablation) | neurally-guided model · Glyph shape matching | similarity | Helped |
| Train on Scribbles, test on Glyphs | neurally-guided model · Glyph shape matching | similarity | Helped |
Closest papers by meaning
- VLMaterial: Procedural Material Generation with Large Vision-Language Models (ICLR 2025 · similarity 0.83)
- VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning (ICLR 2025 · similarity 0.83)
- 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code (NeurIPS 2026 · similarity 0.83)
- Image Inpainting via Tractable Steering of Diffusion Models (ICLR 2024 · similarity 0.82)
- Delta-AI: Local objectives for amortized inference in sparse graphical models (ICLR 2024 · similarity 0.82)
- Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo (ICML 2025 · similarity 0.82)
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.