CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control
cs.GR, cs.LG
Submitted: 2026-05-19
Updated: 2026-10-03
Project page: https://instruct-gs2gs.github.io
Terminology
Sources
- EditP23: 3D Editing via Propagation of Image Prompts to Multi-View
- 3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
- SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
- Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention
- DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing
- Classifier-Free Diffusion Guidance
- HY3D-Bench: Generation of 3D Assets
- GPT-4o System Card
- Shap-E: Generating Conditional 3D Implicit Functions
- Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion
- Point-E: A System for Generating 3D Point Clouds from Complex Prompts
- Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
- Cube: A Roblox View of 3D Intelligence
- GeoCode: Interpretable Shape Programs
- Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
- Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
- Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
- TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editing
- GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks
- Open3D: A Modern Library for 3D Data Processing
Related papers
- SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control
- CADReasoner: Iterative Program Editing for CAD Reverse Engineering
- QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
- DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches
- MotionPersona: Real-Time Locomotion Control across Personas, Bodies, and Styles
- GaussianBench: Physics-Fidelity Evaluation for Gaussian Scene Representations