SpecNeRF: Gaussian Directional Encoding for Specular Reflections

no code implementations • 20 Dec 2023 • Li Ma, Vasu Agrawal, Haithem Turki, Changil Kim, Chen Gao, Pedro Sander, Michael Zollhöfer, Christian Richardt

We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.

HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces

no code implementations • 5 Dec 2023 • Haithem Turki, Vasu Agrawal, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Deva Ramanan, Michael Zollhöfer, Christian Richardt

Neural radiance fields provide state-of-the-art view synthesis quality but tend to be slow to render.

Neural Rendering

PyNeRF: Pyramidal Neural Radiance Fields

1 code implementation • NeurIPS 2023 • Haithem Turki, Michael Zollhöfer, Christian Richardt, Deva Ramanan

Compared to Mip-NeRF, we reduce error rates by 20% while training over 60x faster.

SUDS: Scalable Urban Dynamic Scenes

no code implementations • CVPR 2023 • Haithem Turki, Jason Y. Zhang, Francesco Ferroni, Deva Ramanan

We extend neural radiance fields (NeRFs) to dynamic large-scale urban scenes.

3D Instance Segmentation Novel View Synthesis +2

Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs

1 code implementation • CVPR 2022 • Haithem Turki, Deva Ramanan, Mahadev Satyanarayanan

We use neural radiance fields (NeRFs) to build interactive 3D environments from large-scale visual captures spanning buildings or even multiple city blocks collected primarily from drones.