# PFGS: High Fidelity Point Cloud Rendering via Feature Splatting

arXiv: https://arxiv.org/abs/2407.03857 · HTML: https://mlsanity.com/paper/2407.03857/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 4 Jul 2024.

## Builds on (most cited first, 12 of 12)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality](https://mlsanity.com/paper/2401.16663/) (2024)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection](https://mlsanity.com/paper/2303.10840/) (2023)
- [PointNeRF++: A multi-scale, point-based Neural Radiance Field](https://mlsanity.com/paper/2312.02362/) (2023)
- [Physical Priors Augmented Event-Based 3D Reconstruction](https://mlsanity.com/paper/2401.17121/) (2024)
- [Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation](https://mlsanity.com/paper/2401.14354/) (2024)

## Built on by (most cited first, 7 of 7)

- [OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes](https://mlsanity.com/paper/2510.17719/) (2025)
- [Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians](https://mlsanity.com/paper/2505.09413/) (2025)
- [RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians](https://mlsanity.com/paper/2508.09830/) (2025)
- [Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation](https://mlsanity.com/paper/2605.21258/) (2026)
- [FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2min](https://mlsanity.com/paper/2510.02691/) (2025)
- [MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy](https://mlsanity.com/paper/2605.22597/) (2026)
- [GRIP: Gaussian Rendering as a Cross-Modal Bridge for Image-to-Point Cloud Registration](https://mlsanity.com/paper/2609.25966/) (2026)

## Abstract (arXiv)

Rendering high-fidelity images from sparse point clouds is still challenging. Existing learning-based approaches suffer from either hole artifacts, missing details, or expensive computations. In this paper, we propose a novel framework to render high-quality images from sparse points. This method first attempts to bridge the 3D Gaussian Splatting and point cloud rendering, which includes several cascaded modules. We first use a regressor to estimate Gaussian properties in a point-wise manner, the estimated properties are used to rasterize neural feature descriptors into 2D planes which are extracted from a multiscale extractor. The projected feature volume is gradually decoded toward the final prediction via a multiscale and progressive decoder. The whole pipeline experiences a two-stage training and is driven by our well-designed progressive and multiscale reconstruction loss. Experiments on different benchmarks show the superiority of our method in terms of rendering qualities and the necessities of our main components.