Computer Graphics
TU Braunschweig

D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video


D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video

Dynamic reconstruction and spatiotemporal novel-view synthesis of non-rigidly deforming scenes recently gained increased attention. While existing work achieves impressive quality and performance on multi-view or teleporting camera setups, most methods fail to efficiently and faithfully recover motion and appearance from casual monocular captures. This paper contributes to the field by introducing a new method for dynamic novel view synthesis from monocular video, such as casual smartphone captures. Our approach represents the scene as a dynamic neural point cloud, an implicit time-conditioned point distribution that encodes local geometry and appearance in separate hash-encoded neural feature grids for static and dynamic regions. By sampling a discrete point cloud from our model, we can efficiently render high-quality novel views using a fast differentiable rasterizer and neural rendering network. Similar to recent work, we leverage advances in neural scene analysis by incorporating data-driven priors like monocular depth estimation and object segmentation to resolve motion and depth ambiguities originating from the monocular captures. In addition to guiding the optimization process, we show that these priors can be exploited to explicitly initialize our scene representation to drastically improve optimization speed and final image quality. As evidenced by our experimental evaluation, our dynamic point cloud model not only enables fast optimization and real-time frame rates for interactive applications, but also achieves competitive image quality on monocular benchmark sequences.


Author(s):Moritz Kappel, Florian Hahlbohm, Timon Scholz, Susana Castillo, Christian Theobalt, Martin Eisemann, Vladislav Golyanik, Marcus Magnor
Published:to appear
Type:Article in conference proceedings
Book:Proc. Eurographics
Presented at:Eurographics 2025
Note:To appear
Project(s): Immersive Digital Reality  Real-Action VR  Neural Reconstruction and Rendering of Dynamic Real-World Scenes  Point-Based Neural Rendering 


@inproceedings{kappel2024d-npc,
  title = {D-{NPC}: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video},
  author = {Kappel, Moritz and Hahlbohm, Florian and Scholz, Timon and Castillo, Susana  and Theobalt, Christian and Eisemann, Martin and Golyanik, Vladislav and Magnor, Marcus},
  booktitle = {Proc. Eurographics},
  note = {To appear},
  year = {2025}
}

Authors