# HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene

arXiv: https://arxiv.org/abs/2506.09518 · HTML: https://mlsanity.com/paper/2506.09518/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 55 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 30 of 44)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [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)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes](https://mlsanity.com/paper/2312.14937/) (2023)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [DynIBaR: Neural Dynamic Image-Based Rendering](https://mlsanity.com/paper/2211.11082/) (2022)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://mlsanity.com/paper/2211.11610/) (2022)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [Monocular Dynamic View Synthesis: A Reality Check](https://mlsanity.com/paper/2210.13445/) (2022)
- [VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality](https://mlsanity.com/paper/2401.16663/) (2024)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [OmniRe: Omni Urban Scene Reconstruction](https://mlsanity.com/paper/2408.16760/) (2024)
- [NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields](https://mlsanity.com/paper/2210.15947/) (2022)
- [Efficient Neural Radiance Fields for Interactive Free-viewpoint Video](https://mlsanity.com/paper/2112.01517/) (2021)
- [NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects](https://mlsanity.com/paper/2303.14435/) (2023)
- [DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2205.15723/) (2022)
- [GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis](https://mlsanity.com/paper/2312.11458/) (2023)
- [RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning](https://mlsanity.com/paper/2502.13144/) (2025)
- [Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos](https://mlsanity.com/paper/2304.04452/) (2023)
- [Forward Flow for Novel View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2309.17390/) (2023)

## Built on by (most cited first, 11 of 11)

- [ContextNav: Towards Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2510.04560/) (2025)
- [VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG](https://mlsanity.com/paper/2604.05418/) (2026)
- [DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo](https://mlsanity.com/paper/2506.13215/) (2025)
- [REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance](https://mlsanity.com/paper/2606.09074/) (2026)
- [SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting](https://mlsanity.com/paper/2512.07197/) (2025)
- [SPARE-GS: Structural Parsimony and Resource Efficiency for 3D Gaussian Splatting](https://mlsanity.com/paper/2607.16624/) (2026)
- [2D Gaussians Meet Visual Tokenizer](https://mlsanity.com/paper/2508.13515/) (2025)
- [From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2510.02732/) (2025)
- [LiMT: A Multi-task Liver Image Benchmark Dataset](https://mlsanity.com/paper/2511.19889/) (2025)
- [On the Design of Mixture-of-Experts for Dynamic Gaussian Splatting](https://mlsanity.com/paper/2607.08250/) (2026)
- [4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting](https://mlsanity.com/paper/2605.22342/) (2026)

## Abstract (arXiv)

Reconstructing dynamic 3D scenes from monocular videos remains a fundamental challenge in 3D vision. While 3D Gaussian Splatting (3DGS) achieves real-time rendering in static settings, extending it to dynamic scenes is challenging due to the difficulty of learning structured and temporally consistent motion representations. This challenge often manifests as three limitations in existing methods: redundant Gaussian updates, insufficient motion supervision, and weak modeling of complex non-rigid deformations. These issues collectively hinder coherent and efficient dynamic reconstruction. To address these limitations, we propose HAIF-GS, a unified framework that enables structured and consistent dynamic modeling through sparse anchor-driven deformation. It first identifies motion-relevant regions via an Anchor Filter to suppress redundant updates in static areas. A self-supervised Induced Flow-Guided Deformation module induces anchor motion using multi-frame feature aggregation, eliminating the need for explicit flow labels. To further handle fine-grained deformations, a Hierarchical Anchor Propagation mechanism increases anchor resolution based on motion complexity and propagates multi-level transformations. Extensive experiments on synthetic and real-world benchmarks validate that HAIF-GS significantly outperforms prior dynamic 3DGS methods in rendering quality, temporal coherence, and reconstruction efficiency.