# CheapNVS: Real-Time On-Device Narrow-Baseline Novel View Synthesis

arXiv: https://arxiv.org/abs/2501.14533 · HTML: https://mlsanity.com/paper/2501.14533/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model](https://mlsanity.com/paper/2310.15110/) (2023)
- [Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation](https://mlsanity.com/paper/2312.02145/) (2023)
- [DeepView: View Synthesis with Learned Gradient Descent](https://mlsanity.com/paper/1906.07316/) (2019)
- [3D Photography using Context-aware Layered Depth Inpainting](https://mlsanity.com/paper/2004.04727/) (2020)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [Vision-Only Robot Navigation in a Neural Radiance World](https://mlsanity.com/paper/2110.00168/) (2021)
- [MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction](https://mlsanity.com/paper/2402.12712/) (2024)
- [MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray](https://mlsanity.com/paper/2202.01020/) (2022)
- [Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images](https://mlsanity.com/paper/2205.11733/) (2022)
- [Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction](https://mlsanity.com/paper/2304.12467/) (2023)
- [SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting](https://mlsanity.com/paper/2109.01068/) (2021)
- [One Shot 3D Photography](https://mlsanity.com/paper/2008.12298/) (2020)
- [Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2203.02112/) (2022)
- [Finding Waldo: Towards Efficient Exploration of NeRF Scene Spaces](https://mlsanity.com/paper/2403.04508/) (2024)
- [Single-View View Synthesis with Self-Rectified Pseudo-Stereo](https://mlsanity.com/paper/2304.09527/) (2023)
- [Pose-Free Generalizable Rendering Transformer](https://mlsanity.com/paper/2310.03704/) (2023)
- [Adaptive Mask-based Pyramid Network for Realistic Bokeh Rendering](https://mlsanity.com/paper/2210.16078/) (2022)
- [A Lightweight Neural Network for Monocular View Generation with Occlusion Handling](https://mlsanity.com/paper/2007.12577/) (2020)

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

- [GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction](https://mlsanity.com/paper/2504.06716/) (2025)

## Abstract (arXiv)

Single-view novel view synthesis (NVS) is a notorious problem due to its ill-posed nature, and often requires large, computationally expensive approaches to produce tangible results. In this paper, we propose CheapNVS: a fully end-to-end approach for narrow baseline single-view NVS based on a novel, efficient multiple encoder/decoder design trained in a multi-stage fashion. CheapNVS first approximates the laborious 3D image warping with lightweight learnable modules that are conditioned on the camera pose embeddings of the target view, and then performs inpainting on the occluded regions in parallel to achieve significant performance gains. Once trained on a subset of Open Images dataset, CheapNVS outperforms the state-of-the-art despite being 10 times faster and consuming 6% less memory. Furthermore, CheapNVS runs comfortably in real-time on mobile devices, reaching over 30 FPS on a Samsung Tab 9+.