# Seeing a Rose in Five Thousand Ways

arXiv: https://arxiv.org/abs/2212.04965 · HTML: https://mlsanity.com/paper/2212.04965/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 55 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [Neural Radiance Flow for 4D View Synthesis and Video Processing](https://mlsanity.com/paper/2012.09790/) (2020)
- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [GNeRF: GAN-based Neural Radiance Field without Posed Camera](https://mlsanity.com/paper/2103.15606/) (2021)
- [NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination](https://mlsanity.com/paper/2106.01970/) (2021)
- [SinDDM: A Single Image Denoising Diffusion Model](https://mlsanity.com/paper/2211.16582/) (2022)
- [Unsupervised Learning for Intrinsic Image Decomposition from a Single Image](https://mlsanity.com/paper/1911.09930/) (2019)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [Self-supervised Outdoor Scene Relighting](https://mlsanity.com/paper/2107.03106/) (2021)

## Built on by (most cited first, 13 of 13)

- [4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency](https://mlsanity.com/paper/2312.17225/) (2023)
- [Learning the 3D Fauna of the Web](https://mlsanity.com/paper/2401.02400/) (2024)
- [Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark](https://mlsanity.com/paper/2310.16044/) (2023)
- [Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset](https://mlsanity.com/paper/2504.08541/) (2025)
- [Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space](https://mlsanity.com/paper/2504.21749/) (2025)
- [A Strong and Reproducible Object Detector with Only Public Datasets](https://mlsanity.com/paper/2304.13027/) (2023)
- [Birth and Death of a Rose](https://mlsanity.com/paper/2412.05278/) (2024)
- [Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects](https://mlsanity.com/paper/2401.05236/) (2024)
- [Splat and Replace: 3D Reconstruction with Repetitive Elements](https://mlsanity.com/paper/2506.06462/) (2025)
- [Towards Realistic Example-based Modeling via 3D Gaussian Stitching](https://mlsanity.com/paper/2408.15708/) (2024)
- [GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning](https://mlsanity.com/paper/2312.08744/) (2023)
- [Visual General Intelligence: A White Paper](https://mlsanity.com/paper/2608.25924/) (2026)
- [Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis](https://mlsanity.com/paper/2609.07939/) (2026)

## Abstract (arXiv)

What is a rose, visually? A rose comprises its intrinsics, including the distribution of geometry, texture, and material specific to its object category. With knowledge of these intrinsic properties, we may render roses of different sizes and shapes, in different poses, and under different lighting conditions. In this work, we build a generative model that learns to capture such object intrinsics from a single image, such as a photo of a bouquet. Such an image includes multiple instances of an object type. These instances all share the same intrinsics, but appear different due to a combination of variance within these intrinsics and differences in extrinsic factors, such as pose and illumination. Experiments show that our model successfully learns object intrinsics (distribution of geometry, texture, and material) for a wide range of objects, each from a single Internet image. Our method achieves superior results on multiple downstream tasks, including intrinsic image decomposition, shape and image generation, view synthesis, and relighting.