Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.24986 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914064190406656 |
|---|---|
| author | Wang, Yuhan Chen, Weikai Hu, Zeyu Zhang, Runze Yin, Yingda Wu, Ruoyu Luo, Keyang Qian, Shengju Ma, Yiyan Li, Hongyi Gao, Yuan Zhou, Yuhuan Luo, Hao Wang, Wan Shen, Xiaobin Li, Zhaowei Zhu, Kuixin Hong, Chuanlang Wang, Yueyue Feng, Lijie Wang, Xin Loy, Chen Change |
| author_facet | Wang, Yuhan Chen, Weikai Hu, Zeyu Zhang, Runze Yin, Yingda Wu, Ruoyu Luo, Keyang Qian, Shengju Ma, Yiyan Li, Hongyi Gao, Yuan Zhou, Yuhuan Luo, Hao Wang, Wan Shen, Xiaobin Li, Zhaowei Zhu, Kuixin Hong, Chuanlang Wang, Yueyue Feng, Lijie Wang, Xin Loy, Chen Change |
| contents | In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction offers a promising solution for UGC scenarios by compressing high-resolution meshes into compact, editable representations. Towards this end, effective shape abstraction must therefore be structure-aware, characterized by low overlap between primitives, part-aware alignment, and primitive compactness. We present Light-SQ, a novel superquadric-based optimization framework that explicitly emphasizes structure-awareness from three aspects. (a) We introduce SDF carving to iteratively udpate the target signed distance field, discouraging overlap between primitives. (b) We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition, enabling structural partitioning to drive primitive placement. (c) We implement adaptive residual pruning based on SDF update history to surpress over-segmentation and ensure compact results. In addition, Light-SQ supports multiscale fitting, enabling localized refinement to preserve fine geometric details. To evaluate our method, we introduce 3DGen-Prim, a benchmark extending 3DGen-Bench with new metrics for both reconstruction quality and primitive-level editability. Extensive experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics for complex generated geometry, advancing the feasibility of 3D UGC creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24986 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes Wang, Yuhan Chen, Weikai Hu, Zeyu Zhang, Runze Yin, Yingda Wu, Ruoyu Luo, Keyang Qian, Shengju Ma, Yiyan Li, Hongyi Gao, Yuan Zhou, Yuhuan Luo, Hao Wang, Wan Shen, Xiaobin Li, Zhaowei Zhu, Kuixin Hong, Chuanlang Wang, Yueyue Feng, Lijie Wang, Xin Loy, Chen Change Graphics Artificial Intelligence Computer Vision and Pattern Recognition In user-generated-content (UGC) applications, non-expert users often rely on image-to-3D generative models to create 3D assets. In this context, primitive-based shape abstraction offers a promising solution for UGC scenarios by compressing high-resolution meshes into compact, editable representations. Towards this end, effective shape abstraction must therefore be structure-aware, characterized by low overlap between primitives, part-aware alignment, and primitive compactness. We present Light-SQ, a novel superquadric-based optimization framework that explicitly emphasizes structure-awareness from three aspects. (a) We introduce SDF carving to iteratively udpate the target signed distance field, discouraging overlap between primitives. (b) We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition, enabling structural partitioning to drive primitive placement. (c) We implement adaptive residual pruning based on SDF update history to surpress over-segmentation and ensure compact results. In addition, Light-SQ supports multiscale fitting, enabling localized refinement to preserve fine geometric details. To evaluate our method, we introduce 3DGen-Prim, a benchmark extending 3DGen-Bench with new metrics for both reconstruction quality and primitive-level editability. Extensive experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics for complex generated geometry, advancing the feasibility of 3D UGC creation. |
| title | Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.24986 |