Neural Shell Texture Splatting: More Details and Fewer Primitives

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Xin, Chen, Anpei, Xiong, Jincheng, Dai, Pinxuan, Shen, Yujun, Xu, Weiwei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912504428363776
author Zhang, Xin
Chen, Anpei
Xiong, Jincheng
Dai, Pinxuan
Shen, Yujun
Xu, Weiwei
author_facet Zhang, Xin
Chen, Anpei
Xiong, Jincheng
Dai, Pinxuan
Shen, Yujun
Xu, Weiwei
contents Gaussian splatting techniques have shown promising results in novel view synthesis, achieving high fidelity and efficiency. However, their high reconstruction quality comes at the cost of requiring a large number of primitives. We identify this issue as stemming from the entanglement of geometry and appearance in Gaussian Splatting. To address this, we introduce a neural shell texture, a global representation that encodes texture information around the surface. We use Gaussian primitives as both a geometric representation and texture field samplers, efficiently splatting texture features into image space. Our evaluation demonstrates that this disentanglement enables high parameter efficiency, fine texture detail reconstruction, and easy textured mesh extraction, all while using significantly fewer primitives.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Shell Texture Splatting: More Details and Fewer Primitives
Zhang, Xin
Chen, Anpei
Xiong, Jincheng
Dai, Pinxuan
Shen, Yujun
Xu, Weiwei
Graphics
Computer Vision and Pattern Recognition
Gaussian splatting techniques have shown promising results in novel view synthesis, achieving high fidelity and efficiency. However, their high reconstruction quality comes at the cost of requiring a large number of primitives. We identify this issue as stemming from the entanglement of geometry and appearance in Gaussian Splatting. To address this, we introduce a neural shell texture, a global representation that encodes texture information around the surface. We use Gaussian primitives as both a geometric representation and texture field samplers, efficiently splatting texture features into image space. Our evaluation demonstrates that this disentanglement enables high parameter efficiency, fine texture detail reconstruction, and easy textured mesh extraction, all while using significantly fewer primitives.
title Neural Shell Texture Splatting: More Details and Fewer Primitives
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.20200