SurfScaff3D: Bridging Geometric and Semantic Representations for LLM-based 3D Object Generation
cs.CV
Submitted: 2026-11-08
Updated: 2026-11-08
Project page: https://vcl-iisc.github.io/SurfScaff3D/Electric
Terminology
Sources
- ShapeNet: An Information-Rich 3D Model Repository
- MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement
- Shap-E: Generating Conditional 3D Implicit Functions
- Point-E: A System for Generating 3D Point Clouds from Complex Prompts
- LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models
- Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs