# RPNR: Robust-Perception Neural Reshading

arXiv: https://arxiv.org/abs/2401.14510 · HTML: https://mlsanity.com/paper/2401.14510/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 14 of 14)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image](https://mlsanity.com/paper/1905.02722/) (2019)
- [Single Image Portrait Relighting](https://mlsanity.com/paper/1905.00824/) (2019)
- [DoveNet: Deep Image Harmonization via Domain Verification](https://mlsanity.com/paper/1911.13239/) (2019)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Deep Image Harmonization](https://mlsanity.com/paper/1703.00069/) (2017)
- [Learning Physics-guided Face Relighting under Directional Light](https://mlsanity.com/paper/1906.03355/) (2019)
- [CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering](https://mlsanity.com/paper/1808.08601/) (2018)
- [Fast Spatially-Varying Indoor Lighting Estimation](https://mlsanity.com/paper/1906.03799/) (2019)
- [Deep Sky Modeling for Single Image Outdoor Lighting Estimation](https://mlsanity.com/paper/1905.03897/) (2019)
- [Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination](https://mlsanity.com/paper/2003.08367/) (2020)
- [Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations](https://mlsanity.com/paper/1809.04766/) (2018)
- [Self-Supervised Intrinsic Image Decomposition](https://mlsanity.com/paper/1711.03678/) (2017)

## Abstract (arXiv)

Augmented Reality (AR) applications necessitates methods of inserting needed objects into scenes captured by cameras in a way that is coherent with the surroundings. Common AR applications require the insertion of predefined 3D objects with known properties and shape. This simplifies the problem since it is reduced to extracting an illumination model for the object in that scene by understanding the surrounding light sources. However, it is often not the case that we have information about the properties of an object, especially when we depart from a single source image. Our method renders such source fragments in a coherent way with the target surroundings using only these two images. Our pipeline uses a Deep Image Prior (DIP) network based on a U-Net architecture as the main renderer, alongside robust-feature extracting networks that are used to apply needed losses. Our method does not require any pair-labeled data, and no extensive training on a dataset. We compare our method using qualitative metrics to the baseline methods such as Cut and Paste, Cut And Paste Neural Rendering, and Image Harmonization