# WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images

arXiv: https://arxiv.org/abs/2607.05347 · HTML: https://mlsanity.com/paper/2607.05347/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 7 of 7)

- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://mlsanity.com/paper/2405.17743/) (2024)
- [OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models](https://mlsanity.com/paper/2402.10172/) (2024)
- [Large Language Models for Supply Chain Optimization](https://mlsanity.com/paper/2307.03875/) (2023)
- [A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions](https://mlsanity.com/paper/2508.10047/) (2025)
- [Decision Information Meets Large Language Models: The Future of Explainable Operations Research](https://mlsanity.com/paper/2502.09994/) (2025)
- [NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents](https://mlsanity.com/paper/2601.21372/) (2026)

## Built on by (most cited first, 1 of 1)

- [EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation](https://mlsanity.com/paper/2610.01876/) (2026)

## Abstract (arXiv)

While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce WildSplat, the first feedforward 3D Gaussian Splatting framework capable of appearance-conditioned novel-view synthesis for unposed in-the-wild images. To handle inconsistent photometric conditions, we propose a dual-branch architecture that explicitly decouples geometry from appearance. The geometry branch extracts an appearance-invariant 3D structure and jointly predicts camera poses. To govern the rendering appearance, the appearance branch injects target appearance cues into the content features via a globally pre-modulated cross-attention mechanism. To further prevent feature entanglement, we introduce a joint multi-reference training strategy that stabilizes the training process. Extensive experiments show that WildSplat surpasses existing optimization-based and feedforward methods, achieving state-of-the-art performance in in-the-wild novel view synthesis and appearance editing from sparse inputs in a single forward pass.