# K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Buffers

arXiv: https://arxiv.org/abs/2505.19564 · HTML: https://mlsanity.com/paper/2505.19564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 28 of 28)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [Burst Denoising with Kernel Prediction Networks](https://mlsanity.com/paper/1712.02327/) (2017)
- [StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering](https://mlsanity.com/paper/2402.00525/) (2024)
- [Neural Point Cloud Rendering via Multi-Plane Projection](https://mlsanity.com/paper/1912.04645/) (2019)
- [Neural Point Light Fields](https://mlsanity.com/paper/2112.01473/) (2021)
- [READ: Large-Scale Neural Scene Rendering for Autonomous Driving](https://mlsanity.com/paper/2205.05509/) (2022)
- [Deep Burst Denoising](https://mlsanity.com/paper/1712.05790/) (2017)
- [Basis Prediction Networks for Effective Burst Denoising with Large Kernels](https://mlsanity.com/paper/1912.04421/) (2019)
- [Pointersect: Neural Rendering with Cloud-Ray Intersection](https://mlsanity.com/paper/2304.12390/) (2023)
- [View Synthesis with Sculpted Neural Points](https://mlsanity.com/paper/2205.05869/) (2022)
- [TriVol: Point Cloud Rendering via Triple Volumes](https://mlsanity.com/paper/2303.16485/) (2023)
- [Boosting Point Clouds Rendering via Radiance Mapping](https://mlsanity.com/paper/2210.15107/) (2022)
- [Frequency-Modulated Point Cloud Rendering with Easy Editing](https://mlsanity.com/paper/2303.07596/) (2023)
- [HashPoint: Accelerated Point Searching and Sampling for Neural Rendering](https://mlsanity.com/paper/2404.14044/) (2024)

## Abstract (arXiv)

Neural fields are now the central focus of research in 3D vision and computer graphics. Existing methods mainly focus on various scene representations, such as neural points and 3D Gaussians. However, few works have studied the rendering process to enhance the neural fields. In this work, we propose a plug-in method named K-Buffers that leverages multiple buffers to improve the rendering performance. Our method first renders K buffers from scene representations and constructs K pixel-wise feature maps. Then, We introduce a K-Feature Fusion Network (KFN) to merge the K pixel-wise feature maps. Finally, we adopt a feature decoder to generate the rendering image. We also introduce an acceleration strategy to improve rendering speed and quality. We apply our method to well-known radiance field baselines, including neural point fields and 3D Gaussian Splatting (3DGS). Extensive experiments demonstrate that our method effectively enhances the rendering performance of neural point fields and 3DGS.