DeepAI AI Chat
Log In Sign Up

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

by   Christian Reiser, et al.

NeRF synthesizes novel views of a scene with unprecedented quality by fitting a neural radiance field to RGB images. However, NeRF requires querying a deep Multi-Layer Perceptron (MLP) millions of times, leading to slow rendering times, even on modern GPUs. In this paper, we demonstrate that significant speed-ups are possible by utilizing thousands of tiny MLPs instead of one single large MLP. In our setting, each individual MLP only needs to represent parts of the scene, thus smaller and faster-to-evaluate MLPs can be used. By combining this divide-and-conquer strategy with further optimizations, rendering is accelerated by two orders of magnitude compared to the original NeRF model without incurring high storage costs. Further, using teacher-student distillation for training, we show that this speed-up can be achieved without sacrificing visual quality.


page 1

page 4

page 7

page 8


Neural Lumigraph Rendering

Novel view synthesis is a challenging and ill-posed inverse rendering pr...

Learning Neural Duplex Radiance Fields for Real-Time View Synthesis

Neural radiance fields (NeRFs) enable novel view synthesis with unpreced...

Adaptive Voronoi NeRFs

Neural Radiance Fields (NeRFs) learn to represent a 3D scene from just a...

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

The rendering procedure used by neural radiance fields (NeRF) samples a ...

Plenoxels: Radiance Fields without Neural Networks

We introduce Plenoxels (plenoptic voxels), a system for photorealistic v...

ICARUS: A Specialized Architecture for Neural Radiance Field Rendering

The practical deployment of Neural Radiance Field (NeRF) in rendering ap...

Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses

Learning-based visual relocalizers exhibit leading pose accuracy, but re...

Code Repositories


Code for KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

view repo