Home▸AI & Machine Learning▸Document Layout Attention: Field Extraction

Document Layout Attention: Field Extraction

Interactive 3D simulator of multimodal document-layout attention (LayoutLM-style): watch a transformer link invoice labels to their values by blending spatial position with content similarity, with live extraction accuracy, attention entropy and OCR-noise readouts.

AI & Machine Learning3DModerate60 FPS📱 Mobile-adapted⇄ 2D version
Document Layout Attention: Field Extraction ↗ Open standalone

Intelligent Document Processing (IDP) systems like LayoutLMv3 read a form or invoice not as a flat string of OCR text but as tokens scattered across a 2D page, each carrying both semantic content and spatial position. This simulator renders a mock invoice as a 3D scene of labelled blocks and computes a real self-attention layer over them, blending content similarity with a spatial-proximity bias exactly as a layout-aware transformer does, then draws the resulting label→value attention links as glowing arcs above the page. Tune the spatial bias weight, softmax temperature, simulated OCR noise and link-confidence threshold, or shuffle the layout entirely, and watch live field-extraction accuracy, link count and attention entropy respond.

⚙ Under the hood

Interactive 3D simulator of multimodal document-layout attention (LayoutLM-style): watch a self-attention layer link invoice labels to their values by blending spatial position with content similarity, with live extraction accuracy, entropy and OCR-noise readouts.

document-ailayoutlmself-attentionocrinformation-extractionnlp

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)