mlsanityData to 7 Oct 2026

Seeing a Rose in Five Thousand Ways

arXiv 2212.04965 ↗First posted 9 Dec 2022cs.CVcited by 13

Not on the map. Why?

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.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 36 of its 55 references that are in the map. First posted on arXiv 9 Dec 2022.

Builds on

36 of 55 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  9. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  11. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
24 more
  1. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  2. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  3. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  4. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  5. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  6. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  7. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
  8. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  9. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  10. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  11. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  12. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 204
  13. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  14. 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
  15. 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
  16. 2019Unsupervised Learning for Intrinsic Image Decomposition from a Single Imagecited by 55
  17. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  18. 2021Self-supervised Outdoor Scene Relightingcited by 48
  19. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  20. 2022De-rendering 3D Objects in the Wildcited by 31
  21. 2021De-rendering the World's Revolutionary Artefactscited by 28
  22. 2021Diverse Generation from a Single Video Made Possiblecited by 13
  23. 20223inGAN: Learning a 3D Generative Model from Images of a Self-similar Scenecited by 9
  24. 2022SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scenecited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 4; 2025: 3; 2026: 2.

13 papers.

Sort:

By area:

  1. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistencycited by 117
  2. 2024Learning the 3D Fauna of the Webcited by 58
  3. 2023Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmarkcited by 51
  4. 2025Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Datasetcited by 29
  5. 2025Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Spacecited by 9
  6. 2023A Strong and Reproducible Object Detector with Only Public Datasetscited by 8
  7. 2024Birth and Death of a Rosecited by 7
  8. 2024Structure from Duplicates: Neural Inverse Graphics from a Pile of Objectscited by 5
  9. 2025Splat and Replace: 3D Reconstruction with Repetitive Elementscited by 4
  10. 2024Towards Realistic Example-based Modeling via 3D Gaussian Stitchingcited by 3
  11. 2023GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learningcited by 1
  12. 2026Visual General Intelligence: A White Papercited by 0
1 more
  1. 2026Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesiscited by 0