Research map / Image generation / Text-to-image diffusion
DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
Ruowen Zhao, Junliang Ye, Zhengyi Wang, Guangce Liu, Yiwen Chen, Yikai Wang, Jun Zhu
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 DPO post-training on 5,000 preference pairs (ablation) | DeepMesh · Point-cloud conditioned generation (100 test meshes) | Chamfer Distance: 0.1001 -> 0.0884 | Improved |
| add DPO post-training on 5,000 preference pairs (ablation) | DeepMesh · Point-cloud conditioned generation (100 test meshes) | Hausdorff Distance: 0.1861 -> 0.1708 | Improved |
| add DPO post-training on 5,000 preference pairs (ablation) | DeepMesh · Point-cloud conditioned generation (100 test meshes) | User study preference: 34% -> 37% | Improved |
| use DeepMesh tokenization instead of BPT (smaller vocabulary) | DeepMesh · Mesh tokenization comparison (512 resolution) | Vocabulary size: 40960 -> 4736 | Improved |
| use DeepMesh tokenization instead of BPT | DeepMesh · Mesh tokenization comparison (512 resolution) | Training time (s): 540 -> 480 | Improved |
| use DeepMesh tokenization instead of BPT | DeepMesh · Mesh tokenization comparison (512 resolution) | Compression ratio: 0.26 -> 0.28 | Hurt |
| add data curation filtering (remove low-quality meshes, 800k to about 500k) (ablation) | DeepMesh pre-training · Pre-training loss stability | training loss spikes: 800k to approximately 500k | Improved |
Closest papers by meaning
- Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning (NeurIPS 2025 · similarity 0.88)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (NeurIPS 2025 · similarity 0.87)
- PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance (ICLR 2025 · similarity 0.87)
- MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers (ICLR 2025 · similarity 0.87)
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024 · similarity 0.86)
- DreamAlign: Dynamic Text-to-3D Optimization with Human Preference Alignment (AAAI 2025 · similarity 0.86)
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.
