# Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction

arXiv: https://arxiv.org/abs/2206.05085 · HTML: https://mlsanity.com/paper/2206.05085/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2022.

## Built on by (most cited first, 30 of 61)

- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle](https://mlsanity.com/paper/2312.03431/) (2023)
- [NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Views](https://mlsanity.com/paper/2211.16431/) (2022)
- [Grid-guided Neural Radiance Fields for Large Urban Scenes](https://mlsanity.com/paper/2303.14001/) (2023)
- [Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction](https://mlsanity.com/paper/2208.12697/) (2022)
- [NerfAcc: Efficient Sampling Accelerates NeRFs](https://mlsanity.com/paper/2305.04966/) (2023)
- [Segment Anything in 3D with Radiance Fields](https://mlsanity.com/paper/2304.12308/) (2023)
- [Interactive Segmentation of Radiance Fields](https://mlsanity.com/paper/2212.13545/) (2022)
- [NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields](https://mlsanity.com/paper/2304.14811/) (2023)
- [Binary Radiance Fields](https://mlsanity.com/paper/2306.07581/) (2023)
- [ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field](https://mlsanity.com/paper/2211.13226/) (2022)
- [Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Features](https://mlsanity.com/paper/2303.03003/) (2023)
- [DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelines](https://mlsanity.com/paper/2401.05345/) (2023)
- [SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition](https://mlsanity.com/paper/2401.17857/) (2024)
- [Trim 3D Gaussian Splatting for Accurate Geometry Representation](https://mlsanity.com/paper/2406.07499/) (2024)
- [Cross-Spectral Neural Radiance Fields](https://mlsanity.com/paper/2209.00648/) (2022)
- [Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Training](https://mlsanity.com/paper/2305.02756/) (2023)
- [Thermal-NeRF: Neural Radiance Fields from an Infrared Camera](https://mlsanity.com/paper/2403.10340/) (2024)
- [PeRFception: Perception using Radiance Fields](https://mlsanity.com/paper/2208.11537/) (2022)
- [MV-Map: Offboard HD-Map Generation with Multi-view Consistency](https://mlsanity.com/paper/2305.08851/) (2023)
- [SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes](https://mlsanity.com/paper/2310.13030/) (2023)
- [GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality](https://mlsanity.com/paper/2406.18462/) (2024)
- [VGOS: Voxel Grid Optimization for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2304.13386/) (2023)
- [Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images](https://mlsanity.com/paper/2406.13393/) (2024)
- [Template-free Articulated Neural Point Clouds for Reposable View Synthesis](https://mlsanity.com/paper/2305.19065/) (2023)
- [Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fields](https://mlsanity.com/paper/2311.01815/) (2023)
- [CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations](https://mlsanity.com/paper/2209.01194/) (2022)
- [Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation](https://mlsanity.com/paper/2505.13215/) (2025)
- [GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds](https://mlsanity.com/paper/2308.13175/) (2023)
- [D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video](https://mlsanity.com/paper/2406.10078/) (2024)

## Abstract (arXiv)

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.