TechRxiv
A preprint server for health sciences.
Research
Free
View Pricing
Preprint Submission
Research Dissemination
Version Control
HyperNeRF
4.7
Free HyperNeRF provides high-fidelity 3D reconstruction with good novel-view synthesis, although computationally intensive.
A higher-dimensional representation for topologically varying neural radiance fields.
0 views
0 saves
|
Refined 2/22/2026
About HyperNeRF
HyperNeRF addresses the challenge of modeling topological changes in dynamic scenes using Neural Radiance Fields (NeRF). It lifts NeRFs into a higher-dimensional space, representing the 5D radiance field for each input image as a slice through this hyper-space. Inspired by level set methods, it models changes in scene topology by providing a NeRF with a higher-dimensional input. The architecture extends Nerfies by conditioning the template NeRF on additional higher-dimensional coordinates, effectively creating an 'ambient slicing surface'. This enables the interpolation and novel-view synthesis of scenes with topological variations, outperforming existing methods. It improves average error rates by 4.1% for interpolation and 8.6% for novel-view synthesis, as measured by LPIPS, compared to Nerfies.
Core Capabilities
HyperNeRF addresses the challenge of modeling topological changes in dynamic scenes using Neural Radiance Fields (NeRF).
Main Tasks
Novel View Synthesis
Explore all tools that specialize in novel view synthesis. This domain focus ensures HyperNeRF delivers optimized results for this specific requirement.
