# Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections

arXiv: https://arxiv.org/abs/2407.12306 · HTML: https://mlsanity.com/paper/2407.12306/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 11 of 11)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [Hallucinated Neural Radiance Fields in the Wild](https://mlsanity.com/paper/2111.15246/) (2021)
- [Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections](https://mlsanity.com/paper/2403.15704/) (2024)
- [RobustNeRF: Ignoring Distractors with Robust Losses](https://mlsanity.com/paper/2302.00833/) (2023)
- [SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians](https://mlsanity.com/paper/2403.10427/) (2024)
- [Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collections](https://mlsanity.com/paper/2307.08093/) (2023)

## Built on by (most cited first, 28 of 28)

- [Feat2GS: Probing Visual Foundation Models with Gaussian Splatting](https://mlsanity.com/paper/2412.09606/) (2024)
- [EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis](https://mlsanity.com/paper/2503.20168/) (2025)
- [HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting](https://mlsanity.com/paper/2412.03844/) (2024)
- [DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering](https://mlsanity.com/paper/2411.19756/) (2024)
- [RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS](https://mlsanity.com/paper/2506.02751/) (2025)
- [LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes](https://mlsanity.com/paper/2601.15283/) (2026)
- [Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset](https://mlsanity.com/paper/2506.04224/) (2025)
- [NexusSplats: Efficient 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2411.14514/) (2024)
- [3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling](https://mlsanity.com/paper/2505.21238/) (2025)
- [CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction](https://mlsanity.com/paper/2507.15748/) (2025)
- [EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis](https://mlsanity.com/paper/2601.15951/) (2026)
- [Frequency-Aware Gaussian Splatting Decomposition](https://mlsanity.com/paper/2503.21226/) (2025)
- [Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes](https://mlsanity.com/paper/2505.00734/) (2025)
- [Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction](https://mlsanity.com/paper/2604.23551/) (2026)
- [Taking Language Embedded 3D Gaussian Splatting into the Wild](https://mlsanity.com/paper/2507.19830/) (2025)
- [Non-Aligned Reference Image Quality Assessment for Novel View Synthesis](https://mlsanity.com/paper/2511.08155/) (2025)
- [R3GW: Relightable 3D Gaussians for Outdoor Scenes in the Wild](https://mlsanity.com/paper/2603.02801/) (2026)
- [WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild](https://mlsanity.com/paper/2608.28240/) (2026)
- [Abstract Rendering: Computing All that is Seen in Gaussian Splat Scenes](https://mlsanity.com/paper/2503.00308/) (2025)
- [ExploreGS: a vision-based low overhead framework for 3D scene reconstruction](https://mlsanity.com/paper/2505.10578/) (2025)
- [R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections](https://mlsanity.com/paper/2505.15294/) (2025)
- [NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation](https://mlsanity.com/paper/2510.24335/) (2025)
- [High-fidelity 3D reconstruction for planetary exploration](https://mlsanity.com/paper/2602.13909/) (2026)
- [3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification](https://mlsanity.com/paper/2603.07587/) (2026)
- [Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesis](https://mlsanity.com/paper/2603.20448/) (2026)
- [KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis](https://mlsanity.com/paper/2606.03120/) (2026)
- [Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios](https://mlsanity.com/paper/2606.29496/) (2026)
- [Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis](https://mlsanity.com/paper/2607.05348/) (2026)

## Abstract (arXiv)

Novel view synthesis from unconstrained in-the-wild image collections remains a significant yet challenging task due to photometric variations and transient occluders that complicate accurate scene reconstruction. Previous methods have approached these issues by integrating per-image appearance features embeddings in Neural Radiance Fields (NeRFs). Although 3D Gaussian Splatting (3DGS) offers faster training and real-time rendering, adapting it for unconstrained image collections is non-trivial due to the substantially different architecture. In this paper, we introduce Splatfacto-W, an approach that integrates per-Gaussian neural color features and per-image appearance embeddings into the rasterization process, along with a spherical harmonics-based background model to represent varying photometric appearances and better depict backgrounds. Our key contributions include latent appearance modeling, efficient transient object handling, and precise background modeling. Splatfacto-W delivers high-quality, real-time novel view synthesis with improved scene consistency in in-the-wild scenarios. Our method improves the Peak Signal-to-Noise Ratio (PSNR) by an average of 5.3 dB compared to 3DGS, enhances training speed by 150 times compared to NeRF-based methods, and achieves a similar rendering speed to 3DGS. Additional video results and code integrated into Nerfstudio are available at https://kevinxu02.github.io/splatfactow/.