Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

01/26/2021
by   Towaki Takikawa, et al.
39

Neural signed distance functions (SDFs) are emerging as an effective representation for 3D shapes. State-of-the-art methods typically encode the SDF with a large, fixed-size neural network to approximate complex shapes with implicit surfaces. Rendering with these large networks is, however, computationally expensive since it requires many forward passes through the network for every pixel, making these representations impractical for real-time graphics. We introduce an efficient neural representation that, for the first time, enables real-time rendering of high-fidelity neural SDFs, while achieving state-of-the-art geometry reconstruction quality. We represent implicit surfaces using an octree-based feature volume which adaptively fits shapes with multiple discrete levels of detail (LODs), and enables continuous LOD with SDF interpolation. We further develop an efficient algorithm to directly render our novel neural SDF representation in real-time by querying only the necessary LODs with sparse octree traversal. We show that our representation is 2-3 orders of magnitude more efficient in terms of rendering speed compared to previous works. Furthermore, it produces state-of-the-art reconstruction quality for complex shapes under both 3D geometric and 2D image-space metrics.

READ FULL TEXT

page 1

page 2

page 6

page 7

page 14

page 15

page 16

research
03/22/2021

Neural Lumigraph Rendering

Novel view synthesis is a challenging and ill-posed inverse rendering pr...
research
01/16/2019

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Computer graphics, 3D computer vision and robotics communities have prod...
research
07/11/2022

A Learned Radiance-Field Representation for Complex Luminaires

We propose an efficient method for rendering complex luminaires using a ...
research
05/16/2012

Efficient Topology-Controlled Sampling of Implicit Shapes

Sampling from distributions of implicitly defined shapes enables analysi...
research
11/25/2022

Neural Poisson: Indicator Functions for Neural Fields

Implicit neural field generating signed distance field representations (...
research
02/02/2021

Real-time rendering of complex fractals

This chapter describes how to use intersection and closest-hit shaders t...
research
01/27/2023

A Comparison of Tiny-nerf versus Spatial Representations for 3d Reconstruction

Neural rendering has emerged as a powerful paradigm for synthesizing ima...

Please sign up or login with your details

Forgot password? Click here to reset