# ERUPT: Efficient Rendering with Unposed Patch Transformer

arXiv: https://arxiv.org/abs/2503.24374 · HTML: https://mlsanity.com/paper/2503.24374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis](https://mlsanity.com/paper/2303.16196/) (2023)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations](https://mlsanity.com/paper/2111.13152/) (2021)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing](https://mlsanity.com/paper/2403.17822/) (2024)
- [SparseGS: Sparse View Synthesis using 3D Gaussian Splatting](https://mlsanity.com/paper/2312.00206/) (2023)
- [CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization](https://mlsanity.com/paper/2311.18159/) (2023)
- [Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2404.03613/) (2024)
- [SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field](https://mlsanity.com/paper/2303.13277/) (2023)
- [RUST: Latent Neural Scene Representations from Unposed Imagery](https://mlsanity.com/paper/2211.14306/) (2022)
- [Gaussian Splatting with NeRF-based Color and Opacity](https://mlsanity.com/paper/2312.13729/) (2023)
- [DORSal: Diffusion for Object-centric Representations of Scenes et al](https://mlsanity.com/paper/2306.08068/) (2023)
- [Geometry-biased Transformers for Novel View Synthesis](https://mlsanity.com/paper/2301.04650/) (2023)

## Abstract (arXiv)

This work addresses the problem of novel view synthesis in diverse scenes from small collections of RGB images. We propose ERUPT (Efficient Rendering with Unposed Patch Transformer) a state-of-the-art scene reconstruction model capable of efficient scene rendering using unposed imagery. We introduce patch-based querying, in contrast to existing pixel-based queries, to reduce the compute required to render a target view. This makes our model highly efficient both during training and at inference, capable of rendering at 600 fps on commercial hardware. Notably, our model is designed to use a learned latent camera pose which allows for training using unposed targets in datasets with sparse or inaccurate ground truth camera pose. We show that our approach can generalize on large real-world data and introduce a new benchmark dataset (MSVS-1M) for latent view synthesis using street-view imagery collected from Mapillary. In contrast to NeRF and Gaussian Splatting, which require dense imagery and precise metadata, ERUPT can render novel views of arbitrary scenes with as few as five unposed input images. ERUPT achieves better rendered image quality than current state-of-the-art methods for unposed image synthesis tasks, reduces labeled data requirements by ~95% and decreases computational requirements by an order of magnitude, providing efficient novel view synthesis for diverse real-world scenes.