LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912716048826368 |
|---|---|
| author | Yang, Xinran Lai, Shuichang Lyu, Jiangjing Li, Hongjie Pan, Bowen Li, Yuanqi Guo, Jie Zhou, Zhengkang Guo, Yanwen |
| author_facet | Yang, Xinran Lai, Shuichang Lyu, Jiangjing Li, Hongjie Pan, Bowen Li, Yuanqi Guo, Jie Zhou, Zhengkang Guo, Yanwen |
| contents | Generating high-fidelity 3D contents remains a fundamental challenge due to the complexity of representing arbitrary topologies-such as open surfaces and intricate internal structures-while preserving geometric details. Prevailing methods based on signed distance fields (SDFs) are hampered by costly watertight preprocessing and struggle with non-manifold geometries, while point-cloud representations often suffer from sampling artifacts and surface discontinuities. To overcome these limitations, we propose a novel 3D variational autoencoder (VAE) framework built upon unsigned distance fields (UDFs)-a more robust and computationally efficient representation that naturally handles complex and incomplete shapes. Our core innovation is a local-to-global (LoG) architecture that processes the UDF by partitioning it into uniform subvolumes, termed UBlocks. This architecture couples 3D convolutions for capturing local detail with sparse transformers for enforcing global coherence. A Pad-Average strategy further ensures smooth transitions at subvolume boundaries during reconstruction. This modular design enables seamless scaling to ultra-high resolutions up to $2048^3$-a regime previously unattainable for 3D VAEs. Experiments demonstrate state-of-the-art performance in both reconstruction accuracy and generative quality, yielding superior surface smoothness and geometric flexibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10040 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning Yang, Xinran Lai, Shuichang Lyu, Jiangjing Li, Hongjie Pan, Bowen Li, Yuanqi Guo, Jie Zhou, Zhengkang Guo, Yanwen Computer Vision and Pattern Recognition Generating high-fidelity 3D contents remains a fundamental challenge due to the complexity of representing arbitrary topologies-such as open surfaces and intricate internal structures-while preserving geometric details. Prevailing methods based on signed distance fields (SDFs) are hampered by costly watertight preprocessing and struggle with non-manifold geometries, while point-cloud representations often suffer from sampling artifacts and surface discontinuities. To overcome these limitations, we propose a novel 3D variational autoencoder (VAE) framework built upon unsigned distance fields (UDFs)-a more robust and computationally efficient representation that naturally handles complex and incomplete shapes. Our core innovation is a local-to-global (LoG) architecture that processes the UDF by partitioning it into uniform subvolumes, termed UBlocks. This architecture couples 3D convolutions for capturing local detail with sparse transformers for enforcing global coherence. A Pad-Average strategy further ensures smooth transitions at subvolume boundaries during reconstruction. This modular design enables seamless scaling to ultra-high resolutions up to $2048^3$-a regime previously unattainable for 3D VAEs. Experiments demonstrate state-of-the-art performance in both reconstruction accuracy and generative quality, yielding superior surface smoothness and geometric flexibility. |
| title | LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.10040 |