mlsanityData to 7 Oct 2026

Repopulating Street Scenes

arXiv 2103.16183 ↗First posted 30 Mar 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We present a framework for automatically reconfiguring images of street scenes by populating, depopulating, or repopulating them with objects such as pedestrians or vehicles. Applications of this method include anonymizing images to enhance privacy, generating data augmentations for perception tasks like autonomous driving, and composing scenes to achieve a certain ambiance, such as empty streets in the early morning. At a technical level, our work has three primary contributions: (1) a method for clearing images of objects, (2) a method for estimating sun direction from a single image, and (3) a way to compose objects in scenes that respects scene geometry and illumination. Each component is learned from data with minimal ground truth annotations, by making creative use of large-numbers of short image bursts of street scenes. We demonstrate convincing results on a range of street scenes and illustrate potential applications.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

26 of 42 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  6. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  7. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  8. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  9. 2017Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removalcited by 160
  10. 2020Contextual Residual Aggregation for Ultra High-Resolution Image Inpaintingcited by 124
  11. 2019StructureFlow: Image Inpainting via Structure-aware Appearance Flowcited by 118
  12. 2019Neural Inverse Rendering of an Indoor Scene from a Single Imagecited by 101
14 more
  1. 2019Shadow Removal via Shadow Image Decompositioncited by 96
  2. 2019Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Datacited by 91
  3. 2018ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositingcited by 90
  4. 2019Rendering Synthetic Objects into Legacy Photographscited by 72
  5. 2018Spatial Fusion GAN for Image Synthesiscited by 68
  6. 2019Deep Sky Modeling for Single Image Outdoor Lighting Estimationcited by 66
  7. 2019DeepLight: Learning Illumination for Unconstrained Mobile Mixed Realitycited by 63
  8. 2016Deep Outdoor Illumination Estimationcited by 53
  9. 2019Automatic Scene Inference for 3D Object Compositingcited by 36
  10. 2020Learning to Factorize and Relight a Citycited by 36
  11. 2018Partial Convolution based Paddingcited by 29
  12. 2020Single View Metrology in the Wildcited by 20
  13. 2020People as Scene Probescited by 14
  14. 2016Find your Way by Observing the Sun and Other Semantic Cuescited by 6

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 3; 2024: 2.

6 papers.

  1. 2023OBJECT 3DIT: Language-guided 3D-aware Image Editingcited by 62
  2. 2023UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Videocited by 22
  3. 2021SAC-GAN: Structure-Aware Image Compositioncited by 5
  4. 20243D StreetUnveiler with Semantic-aware 2DGS -- a simple baselinecited by 4
  5. 2023Animating Street Viewcited by 3
  6. 2024E2F-Net: Eyes-to-Face Inpainting via StyleGAN Latent Spacecited by 1