Computer Graphics
TU Braunschweig

INPC: Implicit Neural Point Clouds for Radiance Field Rendering


INPC: Implicit Neural Point Clouds for Radiance Field Rendering

We introduce a new approach for reconstruction and novel view synthesis of unbounded real-world scenes.

In contrast to previous methods using either volumetric fields, grid-based models, or discrete point cloud proxies, we propose a hybrid scene representation, which implicitly encodes the geometry in a continuous octree-based probability field and view-dependent appearance in a multi-resolution hash grid. This allows for extraction of arbitrary explicit point clouds, which can be rendered using rasterization. In doing so, we combine the benefits of both worlds and retain favorable behavior during optimization: Our novel implicit point cloud representation and differentiable bilinear rasterizer enable fast rendering while preserving the fine geometric detail captured by volumetric neural fields. Furthermore, this representation does not depend on priors like structure-from-motion point clouds.

Our method achieves state-of-the-art image quality on common benchmarks. Furthermore, we achieve fast inference at interactive frame rates, and can convert our trained model into a large, explicit point cloud to further enhance performance.


Author(s): Florian Hahlbohm, Linus Franke, Moritz Kappel, Susana Castillo, Martin Eisemann, Marc Stamminger, Marcus Magnor
Published: March 2025
Type: Article in conference proceedings
Book: International Conference on 3D Vision (IEEE)
DOI: 10.1109/3DV66043.2025.00021
Presented at: International Conference on 3D Vision (3DV) 2025
Project(s): Point-Based Neural Rendering  Real-Action VR 

BibTex PDF Webpage Code Video Link Link 



@inproceedings{hahlbohm2024inpc-implicit-neura,
  title = {{INPC}: Implicit Neural Point Clouds for Radiance Field Rendering},
  author = {Hahlbohm, Florian and Franke, Linus and Kappel, Moritz and Castillo, Susana  and Eisemann, Martin and Stamminger, Marc and Magnor, Marcus},
  booktitle = {International Conference on 3D Vision},
  doi = {10.1109/3{DV}66043.2025.00021},
  pages = {168--178},
  month = {Mar},
  year = {2025}
}

Authors