# HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicits

arXiv: https://arxiv.org/abs/2202.01829 · HTML: https://mlsanity.com/paper/2202.01829/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 81 references that are in the map.
- First posted on arXiv 3 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.00681/) (2021)
- [BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration](https://mlsanity.com/paper/1604.01093/) (2016)
- [TransformerFusion: Monocular RGB Scene Reconstruction using Transformers](https://mlsanity.com/paper/2107.02191/) (2021)
- [DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors](https://mlsanity.com/paper/2012.05551/) (2020)
- [Deep Implicit Moving Least-Squares Functions for 3D Reconstruction](https://mlsanity.com/paper/2103.12266/) (2021)
- [A Large Dataset of Object Scans](https://mlsanity.com/paper/1602.02481/) (2016)
- [NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstruction](https://mlsanity.com/paper/2004.04485/) (2020)
- [RoutedFusion: Learning Real-time Depth Map Fusion](https://mlsanity.com/paper/2001.04388/) (2020)
- [NeuralFusion: Online Depth Fusion in Latent Space](https://mlsanity.com/paper/2011.14791/) (2020)
- [SurfelMeshing: Online Surfel-Based Mesh Reconstruction](https://mlsanity.com/paper/1810.00729/) (2018)
- [Kinect Range Sensing: Structured-Light versus Time-of-Flight Kinect](https://mlsanity.com/paper/1505.05459/) (2015)
- [PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction](https://mlsanity.com/paper/1807.11034/) (2018)
- [PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction](https://mlsanity.com/paper/1803.08407/) (2018)
- [A Closed-Form Formulation of HRBF-Based Surface Reconstruction](https://mlsanity.com/paper/1507.02860/) (2015)

## Built on by (most cited first, 8 of 8)

- [GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction](https://mlsanity.com/paper/2309.02436/) (2023)
- [MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstruction](https://mlsanity.com/paper/2308.08741/) (2023)
- [RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting](https://mlsanity.com/paper/2404.19706/) (2024)
- [Monocular Online Reconstruction with Enhanced Detail Preservation](https://mlsanity.com/paper/2505.07887/) (2025)
- [EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly](https://mlsanity.com/paper/2512.01296/) (2025)
- [RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstruction](https://mlsanity.com/paper/2507.17594/) (2025)
- [Cross-Dimensional Refined Learning for Real-Time 3D Visual Perception from Monocular Video](https://mlsanity.com/paper/2303.09248/) (2023)
- [PRISM: Probabilistic Real-Time Inference in Spatial World Models](https://mlsanity.com/paper/2212.02988/) (2022)

## Abstract (arXiv)

Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point- or voxel-based), existing approaches suffer from the accumulation of errors in camera tracking and distortion in the reconstruction, which leads to an unsatisfactory 3D reconstruction. In this paper, we present a method using on-the-fly implicits of Hermite Radial Basis Functions (HRBFs) as a continuous surface representation for camera tracking in an existing RGB-D fusion framework. Furthermore, curvature estimation and confidence evaluation are coherently derived from the inherent surface properties of the on-the-fly HRBF implicits, which devote to a data fusion with better quality. We argue that our continuous but on-the-fly surface representation can effectively mitigate the impact of noise with its robustness and constrain the reconstruction with inherent surface smoothness when being compared with discrete representations. Experimental results on various real-world and synthetic datasets demonstrate that our HRBF-fusion outperforms the state-of-the-art approaches in terms of tracking robustness and reconstruction accuracy.