· 2023
Neuralangelo: High-Fidelity Neural Surface Reconstruction
- 380citations
- 2023year
Short summary
Neuralangelo reconstructs detailed 3D surfaces from images by combining multiresolution 3D hash grids with neural rendering, achieving higher fidelity than previous methods without needing depth data.
AI-generated from the title and abstract; the full text is not read.
Key points
- Neuralangelo reconstructs detailed 3D surfaces from multiview images using neural rendering and multiresolution 3D hash grids.
- The method employs numerical gradients for higher-order derivative computation and a coarse-to-fine optimization on hash grids.
- It achieves significantly higher fidelity in recovering dense 3D surface structures compared to previous methods.
- Neuralangelo can reconstruct detailed large-scale scenes from RGB video captures without auxiliary depth inputs.
AI-generated from the title and abstract; the full text is not read.
Abstract
Neural surface reconstruction has been shown to be powerful for recovering dense 3D surfaces via image-based neural rendering. However, current methods struggle to recover detailed structures of real-world scenes. To address the issue, we present Neuralangelo, which combines the representation power of multiresolution 3D hash grids with neural surface rendering. Two key ingredients enable our approach: (1) numerical gradients for computing higher-order derivatives as a smoothing operation and (2) coarse-to-fine optimization on the hash grids controlling different levels of details. Even without auxiliary inputs such as depth, Neuralangelo can effectively recover dense 3D surface structures from multiview images with fidelity significantly surpassing previous methods, enabling detailed large-scale scene reconstruction from RGB video captures.
The authors' abstract, as published at the source., 2023 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Graphics and Computer-Aided Design
Computer Graphics and Computer-Aided DesignComputer Science