# Towards Efficient Neural Scene Graphs by Learning Consistency Fields

arXiv: https://arxiv.org/abs/2210.04127 · HTML: https://mlsanity.com/paper/2210.04127/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 21 of 21)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [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)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Neural Scene Graphs for Dynamic Scenes](https://mlsanity.com/paper/2011.10379/) (2020)
- [NeX: Real-time View Synthesis with Neural Basis Expansion](https://mlsanity.com/paper/2103.05606/) (2021)
- [Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations](https://mlsanity.com/paper/2012.09988/) (2020)
- [Adversarial Generation of Continuous Images](https://mlsanity.com/paper/2011.12026/) (2020)
- [Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision](https://mlsanity.com/paper/1612.00814/) (2016)
- [VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Field](https://mlsanity.com/paper/2111.13112/) (2021)

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

- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout](https://mlsanity.com/paper/2303.13843/) (2023)
- [AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction](https://mlsanity.com/paper/2407.02598/) (2024)
- [InterFusion: Text-Driven Generation of 3D Human-Object Interaction](https://mlsanity.com/paper/2403.15612/) (2024)
- [OG-Gaussian: Occupancy Based Street Gaussians for Autonomous Driving](https://mlsanity.com/paper/2502.14235/) (2025)
- [Street Gaussians without 3D Object Tracker](https://mlsanity.com/paper/2412.05548/) (2024)
- [DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes](https://mlsanity.com/paper/2508.20965/) (2025)

## Abstract (arXiv)

Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) citeost2021neural extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy ray marching for every image frame becomes a huge burden. In this paper, taking advantage of significant redundancy across adjacent frames in videos, we propose a feature-reusing framework. From the first try of naively reusing the NSG features, however, we learn that it is crucial to disentangle object-intrinsic properties consistent across frames from transient ones. Our proposed method, textitConsistency-Field-based NSG (CF-NSG), reformulates neural radiance fields to additionally consider textitconsistency fields. With disentangled representations, CF-NSG takes full advantage of the feature-reusing scheme and performs an extended degree of scene manipulation in a more controllable manner. We empirically verify that CF-NSG greatly improves the inference efficiency by using 85% less queries than NSG without notable degradation in rendering quality. Code will be available at: https://github.com/ldynx/CF-NSG