embodiedgen/CHANGELOG.md
Xinjie ee03a089b1
feat(sim): Support all simulators and opt asset storage size. (#40)
* feat(sim): Support all simulators and opt asset storage size.
2025-09-25 17:43:28 +08:00

51 lines
2.3 KiB
Markdown

# Changelog
All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0).
## [0.1.5] - 2025-09-25
### Feature
- Support one-click import into all mainstream simulators([isaacsim](https://github.com/isaac-sim/IsaacSim), [mujoco](https://github.com/google-deepmind/mujoco), [genesis](https://github.com/Genesis-Embodied-AI/Genesis), [pybullet](https://github.com/bulletphysics/bullet3), [isaacgym](https://github.com/isaac-sim/IsaacGymEnvs), [sapien](https://github.com/haosulab/SAPIEN)) for assets generated by EmbodiedGen.
- Optimize the storage volume of EmbodiedGen generated assets.
## [0.1.4] - 2025-08-29
### Feature
- Supports importing the output of the EmbodiedGen Layout Generation module with a single `gym.make` command to create multiple parallel simulation environments and interactive 3D worlds.
- Supports coacd-based mesh decomposition for better efficiency and accuracy in physical simulations.
## [0.1.3] - 2025-08-19
### Feature
- Release `layout-cli` 🏞️ Layout(Interactive 3D Worlds) Generation, generate interactive 3D scene from task description.
## [0.1.2] - 2025-07-31
### Feature
- Release `scene3d-cli` 🌍 3D Scene Generation, generate a color mesh and 3DGS scene from text description.
- Release docker file and docker image.
## [0.1.1] - 2025-07-11
### Feature
- Added intelligent quality checkers and auto-retry pipeline for `image-to-3d` and `text-to-3d`.
- Added unit tests for quality checkers.
- `text-to-3d` now supports more `text-to-image` models, pipeline success rate improved to 94%.
## [0.1.0] - 2025-07-04
### Feature
🖼️ Single Image to Physics Realistic 3D Asset
- Generates watertight, simulation-ready 3D meshes with physical attributes.
- Auto-labels semantic and quality tags (geometry, texture, foreground, etc.).
- Produces 2K textures with highlight removal and multi-view fusion.
📝 Text-to-3D Asset Generation
- Creates realistic 3D assets from natural language (English & Chinese).
- Filters assets via QA tags to ensure visual and geometric quality.
🎨 Texture Generation & Editing
- Generates 2K textures from mesh and text with semantic alignment.
- Plug-and-play modules adapt text-to-image models for 3D textures.
- Supports realistic and stylized texture outputs, including text textures.