# Category-level Meta-learned NeRF Priors for Efficient Object Mapping

arXiv: https://arxiv.org/abs/2503.01582 · HTML: https://mlsanity.com/paper/2503.01582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [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)
- [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)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [Learned Initializations for Optimizing Coordinate-Based Neural Representations](https://mlsanity.com/paper/2012.02189/) (2020)
- [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](https://mlsanity.com/paper/2109.01847/) (2021)
- [pymoo: Multi-objective Optimization in Python](https://mlsanity.com/paper/2002.04504/) (2020)
- [Scan2CAD: Learning CAD Model Alignment in RGB-D Scans](https://mlsanity.com/paper/1811.11187/) (2018)
- [Object-Compositional Neural Implicit Surfaces](https://mlsanity.com/paper/2207.09686/) (2022)
- [vMAP: Vectorised Object Mapping for Neural Field SLAM](https://mlsanity.com/paper/2302.01838/) (2023)
- [NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstruction](https://mlsanity.com/paper/2004.04485/) (2020)
- [GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting](https://mlsanity.com/paper/2402.10259/) (2024)
- [FroDO: From Detections to 3D Objects](https://mlsanity.com/paper/2005.05125/) (2020)
- [ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces](https://mlsanity.com/paper/2308.07868/) (2023)
- [DSP-SLAM: Object Oriented SLAM with Deep Shape Priors](https://mlsanity.com/paper/2108.09481/) (2021)
- [Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2205.01823/) (2022)
- [An Object SLAM Framework for Association, Mapping, and High-Level Tasks](https://mlsanity.com/paper/2305.07299/) (2023)
- [RO-MAP: Real-Time Multi-Object Mapping with Neural Radiance Fields](https://mlsanity.com/paper/2304.05735/) (2023)
- [Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors](https://mlsanity.com/paper/2309.09118/) (2023)
- [SQ-SLAM: Monocular Semantic SLAM Based on Superquadric Object Representation](https://mlsanity.com/paper/2209.10817/) (2022)
- [Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors](https://mlsanity.com/paper/2410.05514/) (2024)

## Abstract (arXiv)

In 3D object mapping, category-level priors enable efficient object reconstruction and canonical pose estimation, requiring only a single prior per semantic category (e.g., chair, book, laptop, etc.). DeepSDF has been used predominantly as a category-level shape prior, but it struggles to reconstruct sharp geometry and is computationally expensive. In contrast, NeRFs capture fine details but have yet to be effectively integrated with category-level priors in a real-time multi-object mapping framework. To bridge this gap, we introduce PRENOM, a Prior-based Efficient Neural Object Mapper that integrates category-level priors with object-level NeRFs to enhance reconstruction efficiency and enable canonical object pose estimation. PRENOM gets to know objects on a first-name basis by meta-learning on synthetic reconstruction tasks generated from open-source shape datasets. To account for object category variations, it employs a multi-objective genetic algorithm to optimize the NeRF architecture for each category, balancing reconstruction quality and training time. Additionally, prior-based probabilistic ray sampling directs sampling toward expected object regions, accelerating convergence and improving reconstruction quality under constrained resources. Experimental results highlight the ability of PRENOM to achieve high-quality reconstructions while maintaining computational feasibility. Specifically, comparisons with prior-free NeRF-based approaches on a synthetic dataset show a 21% lower Chamfer distance. Furthermore, evaluations against other approaches using shape priors on a noisy real-world dataset indicate a 13% improvement averaged across all reconstruction metrics, and comparable pose and size estimation accuracy, while being trained for 5× less time. Code available at: https://github.com/snt-arg/PRENOM