# Query Quantized Neural SLAM

arXiv: https://arxiv.org/abs/2412.16476 · HTML: https://mlsanity.com/paper/2412.16476/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 70 references that are in the map.
- First posted on arXiv 21 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes](https://mlsanity.com/paper/2404.10772/) (2024)
- [Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM](https://mlsanity.com/paper/2304.14377/) (2023)
- [NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM](https://mlsanity.com/paper/2302.03594/) (2023)
- [COIN++: Neural Compression Across Modalities](https://mlsanity.com/paper/2201.12904/) (2022)
- [vMAP: Vectorised Object Mapping for Neural Field SLAM](https://mlsanity.com/paper/2302.01838/) (2023)
- [Neural Implicit Dense Semantic SLAM](https://mlsanity.com/paper/2304.14560/) (2023)
- [RGB-D Mapping and Tracking in a Plenoxel Radiance Field](https://mlsanity.com/paper/2307.03404/) (2023)
- [Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning](https://mlsanity.com/paper/2212.08663/) (2022)
- [VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations](https://mlsanity.com/paper/2310.14487/) (2023)
- [InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning](https://mlsanity.com/paper/2303.04508/) (2023)

## Built on by (most cited first, 3 of 3)

- [DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations](https://mlsanity.com/paper/2507.19474/) (2025)
- [Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists](https://mlsanity.com/paper/2603.09277/) (2026)
- [CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM](https://mlsanity.com/paper/2608.01914/) (2026)

## Abstract (arXiv)

Neural implicit representations have shown remarkable abilities in jointly modeling geometry, color, and camera poses in simultaneous localization and mapping (SLAM). Current methods use coordinates, positional encodings, or other geometry features as input to query neural implicit functions for signed distances and color which produce rendering errors to drive the optimization in overfitting image observations. However, due to the run time efficiency requirement in SLAM systems, we are merely allowed to conduct optimization on each frame in few iterations, which is far from enough for neural networks to overfit these queries. The underfitting usually results in severe drifts in camera tracking and artifacts in reconstruction. To resolve this issue, we propose query quantized neural SLAM which uses quantized queries to reduce variations of input for much easier and faster overfitting a frame. To this end, we quantize a query into a discrete representation with a set of codes, and only allow neural networks to observe a finite number of variations. This allows neural networks to become increasingly familiar with these codes after overfitting more and more previous frames. Moreover, we also introduce novel initialization, losses, and argumentation to stabilize the optimization with significant uncertainty in the early optimization stage, constrain the optimization space, and estimate camera poses more accurately. We justify the effectiveness of each design and report visual and numerical comparisons on widely used benchmarks to show our superiority over the latest methods in both reconstruction and camera tracking.