DeepAI AI Chat
Log In Sign Up

Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction

by   Cheng Sun, et al.
National Tsing Hua University

In this technical report, we improve the DVGO framework (called DVGOv2), which is based on Pytorch and uses the simplest dense grid representation. First, we re-implement part of the Pytorch operations with cuda, achieving 2-3x speedup. The cuda extension is automatically compiled just in time. Second, we extend DVGO to support Forward-facing and Unbounded Inward-facing capturing. Third, we improve the space time complexity of the distortion loss proposed by mip-NeRF 360 from O(N^2) to O(N). The distortion loss improves our quality and training speed. Our efficient implementation could allow more future works to benefit from the loss.


page 1

page 2

page 3

page 4


Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

We present a super-fast convergence approach to reconstructing the per-s...

Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction

Direct optimization of interpolated features on multi-resolution voxel g...

Compressing Explicit Voxel Grid Representations: fast NeRFs become also small

NeRFs have revolutionized the world of per-scene radiance field reconstr...

Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields

Temporal interpolation often plays a crucial role to learn meaningful re...

Grid R-CNN Plus: Faster and Better

Grid R-CNN is a well-performed objection detection framework. It transfo...

F^2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories

This paper presents a novel grid-based NeRF called F2-NeRF (Fast-Free-Ne...

Reducing Datacenter Operational Carbon Emissions Effectively by Cooperating with the Grid

Facing growing concerns about power consumption and carbon emissions, cl...

Code Repositories


Efficient distortion loss with O(n) realization.

view repo