GaussFusion: Towards Multimodal 3D Gaussian Pretraining
多模态3D高斯预训练新框架,融合视觉与几何信息,为三维场景理解开辟新路径。
arXiv:2607.05906v1 Announce Type: new Abstract: 3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance,…
多模态3D高斯预训练新框架,融合视觉与几何信息,为三维场景理解开辟新路径。
arXiv:2607.05906v1 Announce Type: new Abstract: 3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance,…
看论文如何用高斯泼溅从RGB-D视频重建可交互数字孪生,为机器人自动化场景带来ICRA新思路。
arXiv:2606.24628v1 Announce Type: cross Abstract: Deploying robots in unstructured real-world environments needs accurate, interactive models of the o…
多视角捕捉面部毛发从稀疏到浓密,无需先验知识即可实现毛流级精细重建
arXiv:2606.08041v1 Announce Type: cross Abstract: Facial hair is a defining trait of personal identity, yet remains a critical bottleneck for digital …
利用滑动框投影实现薄结构的高精度重建,ICIP 2026前沿方法。
arXiv:2606.04251v1 Announce Type: new Abstract: Reconstructing thin 3D structures is challenging due to their sparsity, scale variation, and complex g…
一篇关于神经次表面散射采集与表示的前沿论文,可帮助3D图形从业者理解如何用神经网络高效建模半透明材质
arXiv:2606.02292v1 Announce Type: new Abstract: We present a method to acquire and estimate the sub-surface scattering properties of light transport a…