# BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion

arXiv: https://arxiv.org/abs/2204.01139 · HTML: https://mlsanity.com/paper/2204.01139/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 3 Apr 2022.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://mlsanity.com/paper/2003.10983/) (2020)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [Learning a Predictable and Generative Vector Representation for Objects](https://mlsanity.com/paper/1603.08637/) (2016)
- [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://mlsanity.com/paper/1906.06543/) (2019)
- [DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors](https://mlsanity.com/paper/2012.05551/) (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)
- [Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submaps](https://mlsanity.com/paper/2004.13154/) (2020)
- [InfiniTAM v3: A Framework for Large-Scale 3D Reconstruction with Loop Closure](https://mlsanity.com/paper/1708.00783/) (2017)

## Built on by (most cited first, 29 of 29)

- [Point-SLAM: Dense Neural Point Cloud-based SLAM](https://mlsanity.com/paper/2304.04278/) (2023)
- [ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields](https://mlsanity.com/paper/2211.11704/) (2022)
- [Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting](https://mlsanity.com/paper/2312.10070/) (2023)
- [GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction](https://mlsanity.com/paper/2309.02436/) (2023)
- [Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians](https://mlsanity.com/paper/2405.16544/) (2024)
- [ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images](https://mlsanity.com/paper/2309.08957/) (2023)
- [GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM](https://mlsanity.com/paper/2403.19549/) (2024)
- [ActiveRMAP: Radiance Field for Active Mapping And Planning](https://mlsanity.com/paper/2211.12656/) (2022)
- [NARUTO: Neural Active Reconstruction from Uncertain Target Observations](https://mlsanity.com/paper/2402.18771/) (2024)
- [Neural Visibility Field for Uncertainty-Driven Active Mapping](https://mlsanity.com/paper/2406.06948/) (2024)
- [MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstruction](https://mlsanity.com/paper/2308.08741/) (2023)
- [DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM](https://mlsanity.com/paper/2401.01545/) (2024)
- [PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction](https://mlsanity.com/paper/2310.07449/) (2023)
- [ActiveGAMER: Active GAussian Mapping through Efficient Rendering](https://mlsanity.com/paper/2501.06897/) (2025)
- [NeRFs in Robotics: A Survey](https://mlsanity.com/paper/2405.01333/) (2024)
- [Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection](https://mlsanity.com/paper/2505.07375/) (2025)
- [MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices](https://mlsanity.com/paper/2303.01932/) (2023)
- [Uni-Fusion: Universal Continuous Mapping](https://mlsanity.com/paper/2303.12678/) (2023)
- [3D Reconstruction with Generalizable Neural Fields using Scene Priors](https://mlsanity.com/paper/2309.15164/) (2023)
- [SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors](https://mlsanity.com/paper/2501.06469/) (2025)
- [Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction](https://mlsanity.com/paper/2304.06178/) (2023)
- [Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion](https://mlsanity.com/paper/2404.03070/) (2024)
- [Deblur Gaussian Splatting SLAM](https://mlsanity.com/paper/2503.12572/) (2025)
- [Multi-View Neural 3D Reconstruction of Micro-/Nanostructures with Atomic Force Microscopy](https://mlsanity.com/paper/2401.11541/) (2024)
- [Cues3D: Unleashing the Power of Sole NeRF for Consistent and Unique Instances in Open-Vocabulary 3D Panoptic Segmentation](https://mlsanity.com/paper/2505.00378/) (2025)
- [OAAFormer: Robust and Efficient Point Cloud Registration Through Overlapping-Aware Attention in Transformer](https://mlsanity.com/paper/2310.09817/) (2023)
- [LISNeRF Mapping: LiDAR-based Implicit Mapping via Semantic Neural Fields for Large-Scale 3D Scenes](https://mlsanity.com/paper/2311.02313/) (2023)
- [DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2608.01178/) (2026)
- [STARS-GS: Structure-Aware Regularized Gaussian Splatting for Large-Scale Aerial Surface Reconstruction](https://mlsanity.com/paper/2609.03447/) (2026)

## Abstract (arXiv)

Dense 3D reconstruction from a stream of depth images is the key to many mixed reality and robotic applications. Although methods based on Truncated Signed Distance Function (TSDF) Fusion have advanced the field over the years, the TSDF volume representation is confronted with striking a balance between the robustness to noisy measurements and maintaining the level of detail. We present Bi-level Neural Volume Fusion (BNV-Fusion), which leverages recent advances in neural implicit representations and neural rendering for dense 3D reconstruction. In order to incrementally integrate new depth maps into a global neural implicit representation, we propose a novel bi-level fusion strategy that considers both efficiency and reconstruction quality by design. We evaluate the proposed method on multiple datasets quantitatively and qualitatively, demonstrating a significant improvement over existing methods.