# Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2506.03538 · HTML: https://mlsanity.com/paper/2506.03538/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## 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)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [Urban Radiance Fields](https://mlsanity.com/paper/2111.14643/) (2021)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [WildGaussians: 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2407.08447/) (2024)
- [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)
- [NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild](https://mlsanity.com/paper/2405.18715/) (2024)
- [SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians](https://mlsanity.com/paper/2403.10427/) (2024)
- [SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting](https://mlsanity.com/paper/2406.20055/) (2024)
- [Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections](https://mlsanity.com/paper/2406.10373/) (2024)
- [NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods](https://mlsanity.com/paper/2406.17345/) (2024)
- [HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting](https://mlsanity.com/paper/2412.03844/) (2024)

## Built on by (most cited first, 6 of 6)

- [PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting](https://mlsanity.com/paper/2604.12580/) (2026)
- [Wild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection](https://mlsanity.com/paper/2606.11894/) (2026)
- [WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild](https://mlsanity.com/paper/2608.28240/) (2026)
- [DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis](https://mlsanity.com/paper/2604.13416/) (2026)
- [HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization](https://mlsanity.com/paper/2605.13073/) (2026)
- [Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios](https://mlsanity.com/paper/2606.29496/) (2026)

## Abstract (arXiv)

3D reconstruction from in-the-wild images remains a challenging task due to inconsistent lighting conditions and transient distractors. Existing methods typically rely on heuristic strategies to handle the low-quality training data, which often struggle to produce stable and consistent reconstructions, frequently resulting in visual artifacts. In this work, we propose modelname, a novel framework that leverages the stochastic nature of these artifacts: they tend to vary across different training runs due to minor randomness. Specifically, our method trains two 3D Gaussian Splatting (3DGS) models in parallel, enforcing a consistency constraint that encourages convergence on reliable scene geometry while suppressing inconsistent artifacts. To prevent the two models from collapsing into similar failure modes due to confirmation bias, we introduce a divergent masking strategy that applies two complementary masks: a multi-cue adaptive mask and a self-supervised soft mask, which leads to an asymmetric training process of the two models, reducing shared error modes. In addition, to improve the efficiency of model training, we introduce a lightweight variant called Dynamic EMA Proxy, which replaces one of the two models with a dynamically updated Exponential Moving Average (EMA) proxy, and employs an alternating masking strategy to preserve divergence. Extensive experiments on challenging real-world datasets demonstrate that our method consistently outperforms existing approaches while achieving high efficiency. See the project website at https://steveli88.github.io/AsymGS.