mlsanityData to 7 Oct 2026

DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering

arXiv 2104.13602 ↗First posted 28 Apr 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose DeRenderNet, a deep neural network to decompose the albedo and latent lighting, and render shape-(in)dependent shadings, given a single image of an outdoor urban scene, trained in a self-supervised manner. To achieve this goal, we propose to use the albedo maps extracted from scenes in videogames as direct supervision and pre-compute the normal and shadow prior maps based on the depth maps provided as indirect supervision. Compared with state-of-the-art intrinsic image decomposition methods, DeRenderNet produces shadow-free albedo maps with clean details and an accurate prediction of shadows in the shape-independent shading, which is shown to be effective in re-rendering and improving the accuracy of high-level vision tasks for urban scenes.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 28 Apr 2021.

Builds on

24 of 43 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  5. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  6. 2019Mask Scoring R-CNNcited by 265
  7. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 202
  8. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  9. 2017SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wildcited by 110
  10. 2019Neural Inverse Rendering of an Indoor Scene from a Single Imagecited by 101
  11. 2018InverseRenderNet: Learning single image inverse renderingcited by 100
  12. 2018CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Renderingcited by 85
12 more
  1. 2018Learning Intrinsic Image Decomposition from Watching the Worldcited by 74
  2. 2019Deep Sky Modeling for Single Image Outdoor Lighting Estimationcited by 66
  3. 2016Deep Shading: Convolutional Neural Networks for Screen-Space Shadingcited by 46
  4. 2016Learning Non-Lambertian Object Intrinsics across ShapeNet Categoriescited by 42
  5. 2020Learning to Factorize and Relight a Citycited by 36
  6. 2016Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networkscited by 35
  7. 2018LIME: Live Intrinsic Material Estimationcited by 33
  8. 2015Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regressioncited by 32
  9. 2015Learning Data-driven Reflectance Priors for Intrinsic Image Decompositioncited by 24
  10. 2017Shading Annotations in the Wildcited by 19
  11. 2016Reflectance Adaptive Filtering Improves Intrinsic Image Estimationcited by 18
  12. 2018Learning to Estimate Indoor Lighting from 3D Objectscited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 0; 2026: 2.

6 papers.

  1. 2022Physically-Based Editing of Indoor Scene Lighting from a Single Imagecited by 62
  2. 2023Unsupervised Intrinsic Image Decomposition with LiDAR Intensitycited by 6
  3. 2026LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditionscited by 4
  4. 2022Discriminative feature encoding for intrinsic image decompositioncited by 1
  5. 2024Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Trainingcited by 0
  6. 2026BRDFusion: Physics Meets Generation for Urban Scene Inverse Renderingcited by 0