Research map / Image generation / Text-to-image diffusion
Vinedresser3D: Towards Agentic Text-guided 3D Editing
Yankuan Chi, Xiang Li, Zixuan Huang, James Matthew Rehg
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Trellis-text interleaved with Trellis-image in denoising (ablation) | Vinedresser3D · 3D editing ablation | FID: 30.59 -> 29.49 | Improved |
| add Trellis-text interleaved with Trellis-image in denoising (ablation) | Vinedresser3D · 3D editing ablation | PSNR: 28.06 -> 29.45 | Improved |
| add detected editing region mask (Redit) (ablation) | Vinedresser3D · 3D editing ablation | PSNR/FID: PSNR 25.65 -> 29.45; FID 33.95 -> 29.49 | Improved |
| use automatic MLLM-detected region instead of human 3D mask (ablation) | Vinedresser3D · Text-guided 3D editing | PSNR: 37.69 -> 29.45 | Hurt |
| use automatic MLLM-detected region instead of human 3D mask (ablation) | Vinedresser3D · Text-guided 3D editing | CLIP-T: 0.252 -> 0.252 | No clear effect |
| use MLLM text and image guidance with auto region instead of Trellis with human mask | Trellis editing · Text-guided 3D editing | CLIP-T: 0.247 -> 0.252 | Improved |
| use Vinedresser3D (no mask) instead of Trellis with human mask | Trellis editing · Text-guided 3D editing | preservation (PSNR/SSIM/LPIPS/CD): PSNR 37.35 -> 29.45; CD 0.010 -> 0.016 | Hurt |
| use Vinedresser3D (no mask) instead of Trellis with human mask | Trellis editing · Text-guided 3D editing | FID: 31.10 -> 29.49 | Improved |
| use Vinedresser3D instead of VoxHammer | VoxHammer · User study | win rate: 89.8% / 79.3% / 90.2% win rates | Improved |
Closest papers by meaning
- Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts (ICLR 2024 · similarity 0.87)
- SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds (CVPR 2024 · similarity 0.86)
- EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing (ICLR 2025 · similarity 0.86)
- LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration (NeurIPS 2025 · similarity 0.86)
- FocalDreamer: Text-Driven 3D Editing via Focal-Fusion Assembly (AAAI 2024 · similarity 0.85)
- EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing (ICLR 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
