Spaces:
Running
title: Code4Scene
emoji: 🏗️
colorFrom: yellow
colorTo: gray
sdk: static
app_file: index.html
pinned: false
short_description: Benchmarking coding agents that build and edit 3D scenes
Code4Scene
Project page for Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes: the leaderboard on the 95-case public set, the paper's takeaways, and selected cases whose saved Unreal Engine scenes can be viewed in 3D.
Paper: arXiv:2609.36777 · Code: SimWorld-AI/Code4Scene
Part of the SimWorld project.
Website design
Layout, navigation, wireframe mark, typography and card geometry follow the user-provided BuildingBench design. The bar chart rendering and company palette are adapted from its Figure Kit, specifically bar-static/build.py. All scores, configurations, authors, media, models and evaluator content remain Code4Scene's. The original 95-public-case paper evaluation is distinguished from the current 201 public cases and the 320-case full benchmark target, including private cases.
The reference toolkit's Inter, IBM Plex Mono and Source Serif 4 font files are bundled with their original SIL Open Font License notices in assets/fonts/. Provider marks are from the toolkit's Lobehub icons, used to identify the corresponding model providers.
Deployment remains this Hugging Face static Space: index.html and cases.html, with the existing media/model paths and headers. The pre-restyle version is recoverable at commit 9ff787d0f9d72905d92f780da56bd2229782b981.
The Pareto renderer (assets/pareto.js) ports the reference toolkit's reversed logarithmic cost axis, connected frontier, provider palette and greedy collision-aware label placement. data/pareto.json combines unrounded scores from the existing data/site.js with exact mean costs from the original published tables; all three task views recompute non-dominance from those values. The table displays three decimals but sorts at source precision.
Homepage scenes (assets/scene-cards.js) adapt BuildingBench's shared WebGL renderer and per-view canvas engine. Existing public packed models are decoded with the same adapter as cases.html; geometry and the full case explorer remain unchanged. Visible scenes load automatically; repeated scenes share decoded assets. Drag or arrow keys orbit, wheel or +/- zoom, and the pause control stops rotation. Both Image-to-Scene cards switch between the saved repair, corrupted input and ground truth using the reference camera.
Interaction and loading reliability
Task Format switches the entire construction/editing example, including instructions, inputs, saved output and evaluator. Bar marks, labels and Pareto points share pointer, keyboard and tap tooltips with source-precision scores and costs in data/leaderboard-details.json. The ranking supports filtering and source-precision sorting.
Homepage model work uses a shared two-job download/decode queue. Hidden/offscreen views release their request; stale results cannot replace the selected state. Card textures are limited to 512px and render resolution is bounded, while original model files and the full case explorer stay intact. Idle decoded assets are evicted; the 128 MiB cache target is not a hard limit on currently visible geometry. Downloads show progress, abort after 20 seconds without data or 90 seconds total, retry once, then expose an explicit Retry button. Context loss pauses drawing and restoration rebuilds the environment; failures expose recovery instead of an indefinite loading overlay.
Queue tests: node --test tests/scene-assets.test.mjs. Browser QA includes public-model cold loads, quick scrolling, task/repair switching, desktop/mobile resize, forced HTTP failures, stalled downloads, retry and WebGL context loss.