Generating 3D House Wireframes with Semantics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929424231825408 |
|---|---|
| author | Ma, Xueqi Liu, Yilin Zhou, Wenjun Wang, Ruowei Huang, Hui |
| author_facet | Ma, Xueqi Liu, Yilin Zhou, Wenjun Wang, Ruowei Huang, Hui |
| contents | We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified wire-based representation for improved coherence in learning 3D wireframe structures. By re-ordering wire sequences based on semantic meanings, we facilitate seamless semantic integration during sequence generation. Our two-phase technique merges a graph-based autoencoder with a transformer-based decoder to learn latent geometric tokens and generate semantic-aware wireframes. Through iterative prediction and decoding during inference, our model produces detailed wireframes that can be easily segmented into distinct components, such as walls, roofs, and rooms, reflecting the semantic essence of the shape. Empirical results on a comprehensive house dataset validate the superior accuracy, novelty, and semantic fidelity of our model compared to existing generative models. More results and details can be found on https://vcc.tech/research/2024/3DWire. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12267 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generating 3D House Wireframes with Semantics Ma, Xueqi Liu, Yilin Zhou, Wenjun Wang, Ruowei Huang, Hui Computer Vision and Pattern Recognition Graphics We present a new approach for generating 3D house wireframes with semantic enrichment using an autoregressive model. Unlike conventional generative models that independently process vertices, edges, and faces, our approach employs a unified wire-based representation for improved coherence in learning 3D wireframe structures. By re-ordering wire sequences based on semantic meanings, we facilitate seamless semantic integration during sequence generation. Our two-phase technique merges a graph-based autoencoder with a transformer-based decoder to learn latent geometric tokens and generate semantic-aware wireframes. Through iterative prediction and decoding during inference, our model produces detailed wireframes that can be easily segmented into distinct components, such as walls, roofs, and rooms, reflecting the semantic essence of the shape. Empirical results on a comprehensive house dataset validate the superior accuracy, novelty, and semantic fidelity of our model compared to existing generative models. More results and details can be found on https://vcc.tech/research/2024/3DWire. |
| title | Generating 3D House Wireframes with Semantics |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2407.12267 |