mlsanityData to 7 Oct 2026

SurfaceNet: Adversarial SVBRDF Estimation from a Single Image

arXiv 2107.11298 ↗First posted 23 Jul 2021cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

In this paper we present SurfaceNet, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image. We pose the problem as an image translation task and propose a novel patch-based generative adversarial network (GAN) that is able to produce high-quality, high-resolution surface reflectance maps. The employment of the GAN paradigm has a twofold objective: 1) allowing the model to recover finer details than standard translation models; 2) reducing the domain shift between synthetic and real data distributions in an unsupervised way. An extensive evaluation, carried out on a public benchmark of synthetic and real images under different illumination conditions, shows that SurfaceNet largely outperforms existing SVBRDF reconstruction methods, both quantitatively and qualitatively. Furthermore, SurfaceNet exhibits a remarkable ability in generating high-quality maps from real samples without any supervision at training time.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 23 Jul 2021.

Builds on

14 of 27 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  5. 2013Describing Textures in the Wildcited by 2,110
  6. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  7. 2018Single-Image SVBRDF Capture with a Rendering-Aware Deep Networkcited by 116
  8. 2018Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Imagecited by 66
  9. 2020Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Imagescited by 65
  10. 2018Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networkscited by 51
  11. 2019Flexible SVBRDF Capture with a Multi-Image Deep Networkcited by 50
  12. 2015Loss Functions for Neural Networks for Image Processingcited by 41
2 more
  1. 2020MaterialGAN: Reflectance Capture using a Generative SVBRDF Modelcited by 33
  2. 2020Guided Fine-Tuning for Large-Scale Material Transfercited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 7; 2025: 11; 2026: 1.

25 papers.

Sort:

By area:

  1. 2022Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptationcited by 67
  2. 2023ControlMat: A Controlled Generative Approach to Material Capturecited by 50
  3. 2024MatSynth: A Modern PBR Materials Datasetcited by 42
  4. 2023MatFuse: Controllable Material Generation with Diffusion Modelscited by 39
  5. 2024MatFusion: A Generative Diffusion Model for SVBRDF Capturecited by 31
  6. 2023Material Palette: Extraction of Materials from a Single Imagecited by 28
  7. 2023UMat: Uncertainty-Aware Single Image High Resolution Material Capturecited by 11
  8. 2025VLMaterial: Procedural Material Generation with Large Vision-Language Modelscited by 9
  9. 2024MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assetscited by 6
  10. 2024ReflectanceFusion: Diffusion-based text to SVBRDF Generationcited by 5
  11. 2025Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Imagescited by 5
  12. 2024StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learningcited by 4
13 more
  1. 2025MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesiscited by 3
  2. 2025MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Modelscited by 2
  3. 2024FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Clothing Imagescited by 1
  4. 2025Single-image Reflectance and Transmittance Estimation from Any Flatbed Scannercited by 1
  5. 2025RETRO: REthinking Tactile Representation Learning with Material PriOrscited by 1
  6. 2025DualMat: PBR Material Estimation via Coherent Dual-Path Diffusioncited by 1
  7. 2025Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gapcited by 1
  8. 2022Diffuse Map Guiding Unsupervised Generative Adversarial Network for SVBRDF Estimationcited by 0
  9. 2024Neural Appearance Modeling From Single Imagescited by 0
  10. 2025Design of an Expression Recognition Solution Based on the Global Channel-Spatial Attention Mechanism and Proportional Criterion Fusioncited by 0
  11. 2025SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregationcited by 0
  12. 2025Phieat: Physically Grounded Material Feature Representationcited by 0
  13. 2026DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformercited by 0