# PREF: Predictability Regularized Neural Motion Fields

arXiv: https://arxiv.org/abs/2209.10691 · HTML: https://mlsanity.com/paper/2209.10691/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 64 references that are in the map.
- First posted on arXiv 21 Sep 2022.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video](https://mlsanity.com/paper/2012.12247/) (2020)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [Space-time Neural Irradiance Fields for Free-Viewpoint Video](https://mlsanity.com/paper/2011.12950/) (2020)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Neural Radiance Flow for 4D View Synthesis and Video Processing](https://mlsanity.com/paper/2012.09790/) (2020)
- [Neural Unsigned Distance Fields for Implicit Function Learning](https://mlsanity.com/paper/2010.13938/) (2020)
- [Urban Radiance Fields](https://mlsanity.com/paper/2111.14643/) (2021)
- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](https://mlsanity.com/paper/2109.01847/) (2021)
- [HeadNeRF: A Real-time NeRF-based Parametric Head Model](https://mlsanity.com/paper/2112.05637/) (2021)
- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)

## Built on by (most cited first, 13 of 13)

- [NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)](https://mlsanity.com/paper/2210.00379/) (2022)
- [Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction](https://mlsanity.com/paper/2312.01196/) (2023)
- [DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation](https://mlsanity.com/paper/2312.00583/) (2023)
- [Dynamic Point Fields](https://mlsanity.com/paper/2304.02626/) (2023)
- [Recent Trends in 3D Reconstruction of General Non-Rigid Scenes](https://mlsanity.com/paper/2403.15064/) (2024)
- [7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting](https://mlsanity.com/paper/2503.07946/) (2025)
- [DaReNeRF: Direction-aware Representation for Dynamic Scenes](https://mlsanity.com/paper/2403.02265/) (2024)
- [SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes](https://mlsanity.com/paper/2308.08258/) (2023)
- [TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction](https://mlsanity.com/paper/2411.11941/) (2024)
- [Consistent Instance Field for Dynamic Scene Understanding](https://mlsanity.com/paper/2512.14126/) (2025)
- [Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images](https://mlsanity.com/paper/2407.09694/) (2024)
- [DaRePlane: Direction-aware Representations for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2410.14169/) (2024)
- [Paving the Way for Point Cloud Video Representation Learning Using A PDE Model](https://mlsanity.com/paper/2606.01604/) (2026)

## Abstract (arXiv)

Knowing the 3D motions in a dynamic scene is essential to many vision applications. Recent progress is mainly focused on estimating the activity of some specific elements like humans. In this paper, we leverage a neural motion field for estimating the motion of all points in a multiview setting. Modeling the motion from a dynamic scene with multiview data is challenging due to the ambiguities in points of similar color and points with time-varying color. We propose to regularize the estimated motion to be predictable. If the motion from previous frames is known, then the motion in the near future should be predictable. Therefore, we introduce a predictability regularization by first conditioning the estimated motion on latent embeddings, then by adopting a predictor network to enforce predictability on the embeddings. The proposed framework PREF (Predictability REgularized Fields) achieves on par or better results than state-of-the-art neural motion field-based dynamic scene representation methods, while requiring no prior knowledge of the scene.