# Embedding Novel Views in a Single JPEG Image

arXiv: https://arxiv.org/abs/2108.13003 · HTML: https://mlsanity.com/paper/2108.13003/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 30 Aug 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Single-View View Synthesis with Multiplane Images](https://mlsanity.com/paper/2004.11364/) (2020)
- [DeepView: View Synthesis with Learned Gradient Descent](https://mlsanity.com/paper/1906.07316/) (2019)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)
- [3D Photography using Context-aware Layered Depth Inpainting](https://mlsanity.com/paper/2004.04727/) (2020)
- [Pushing the Boundaries of View Extrapolation with Multiplane Images](https://mlsanity.com/paper/1905.00413/) (2019)
- [Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes](https://mlsanity.com/paper/1904.11112/) (2019)
- [Generating Steganographic Images via Adversarial Training](https://mlsanity.com/paper/1703.00371/) (2017)
- [Semantic View Synthesis](https://mlsanity.com/paper/2008.10598/) (2020)
- [Generative View Synthesis: From Single-view Semantics to Novel-view Images](https://mlsanity.com/paper/2008.09106/) (2020)
- [Mononizing Binocular Videos](https://mlsanity.com/paper/2009.01424/) (2020)

## Built on by (most cited first, 10 of 10)

- [Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2307.11335/) (2023)
- [StegaNeRF: Embedding Invisible Information within Neural Radiance Fields](https://mlsanity.com/paper/2212.01602/) (2022)
- [Scale-arbitrary Invertible Image Downscaling](https://mlsanity.com/paper/2201.12576/) (2022)
- [Real-time 6K Image Rescaling with Rate-distortion Optimization](https://mlsanity.com/paper/2304.01064/) (2023)
- [InvVis: Large-Scale Data Embedding for Invertible Visualization](https://mlsanity.com/paper/2307.16176/) (2023)
- [ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Images](https://mlsanity.com/paper/2404.16825/) (2024)
- [Robust Message Embedding via Attention Flow-Based Steganography](https://mlsanity.com/paper/2405.16414/) (2024)
- [Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noise](https://mlsanity.com/paper/2401.01216/) (2024)
- [VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrieval](https://mlsanity.com/paper/2507.14459/) (2025)
- [Single-view Neural Radiance Fields with Depth Teacher](https://mlsanity.com/paper/2303.09952/) (2023)

## Abstract (arXiv)

We propose a novel approach for embedding novel views in a single JPEG image while preserving the perceptual fidelity of the modified JPEG image and the restored novel views. We adopt the popular novel view synthesis representation of multiplane images (MPIs). Our model first encodes 32 MPI layers (totally 128 channels) into a 3-channel JPEG image that can be decoded for MPIs to render novel views, with an embedding capacity of 1024 bits per pixel. We conducted experiments on public datasets with different novel view synthesis methods, and the results show that the proposed method can restore high-fidelity novel views from a slightly modified JPEG image. Furthermore, our method is robust to JPEG compression, color adjusting, and cropping. Our source code will be publicly available.