Research map / 3D vision / 3D generation
Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
Wenyue Chen, Wenjue Chen, Peng Li, Qinghe Wang, XU JIA, Heliang Zheng, Rongfei Jia, Yuan Liu, Ronggang Wang
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 |
|---|---|---|---|
| use MMDiT hidden states instead of VAE encoder features (ablation) | Know3D · TexVerse subset IoU | IoU: 0.308 -> 0.352 | Improved |
| use MMDiT hidden states instead of VAE encoder features (ablation) | Know3D · TexVerse subset CD | Chamfer Distance: 2.803 -> 2.262 | Improved |
| use MMDiT hidden states instead of DINOv3 features (ablation) | Know3D · TexVerse subset IoU | IoU: 0.342 -> 0.352 | Improved |
| use MMDiT hidden states instead of DINOv3 features (ablation) | Know3D · TexVerse subset CD | Chamfer Distance: 2.385 -> 2.262 | Improved |
| extract features at t=0.25 instead of t=0 (ablation) | Know3D · TexVerse subset IoU | IoU: 0.343 -> 0.352 | Improved |
| extract features at t=0.25 instead of t=0.75 (ablation) | Know3D · TexVerse subset CD | Chamfer Distance: 2.452 -> 2.262 | Improved |
| extract features at t=0.25 instead of t=0.5 (ablation) | Know3D · TexVerse subset IoU | IoU: 0.349 -> 0.352 | No clear effect |
| Know3D versus TRELLIS.2 baseline | Know3D · HY3D-Bench-test | Uni3D: 0.3308 -> 0.3518 | Improved |
| Know3D versus Hunyuan3D-2MV with generated back view | Know3D · HY3D-Bench-test | ULIP: 0.2108 -> 0.2174 | Improved |
| Know3D versus TRELLIS | Know3D · HY3D-Bench-val | ULIP: 0.2133 -> 0.2127 | Hurt |
| Know3D versus Hunyuan3D-2.1 | Know3D · HY3D-Bench-val | Uni3D: 0.3433 -> 0.3512 | Improved |
Closest papers by meaning
- Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation (ICML 2026 · similarity 0.91)
- Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering (NeurIPS 2026 · similarity 0.88)
- 3D-VLA: A 3D Vision-Language-Action Generative World Model (ICML 2024 · similarity 0.88)
- IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering (NeurIPS 2025 · similarity 0.88)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.88)
- GenSpace: Benchmarking Spatially-Aware Image Generation (NeurIPS 2025 · similarity 0.88)
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.
