# SurfaceNet: Adversarial SVBRDF Estimation from a Single Image

arXiv: https://arxiv.org/abs/2107.11298 · HTML: https://mlsanity.com/paper/2107.11298/

## Key facts

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

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Single-Image SVBRDF Capture with a Rendering-Aware Deep Network](https://mlsanity.com/paper/1810.09718/) (2018)
- [Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image](https://mlsanity.com/paper/1804.05790/) (2018)
- [Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images](https://mlsanity.com/paper/2003.12642/) (2020)
- [Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks](https://mlsanity.com/paper/1809.00886/) (2018)
- [Flexible SVBRDF Capture with a Multi-Image Deep Network](https://mlsanity.com/paper/1906.11557/) (2019)
- [Loss Functions for Neural Networks for Image Processing](https://mlsanity.com/paper/1511.08861/) (2015)
- [MaterialGAN: Reflectance Capture using a Generative SVBRDF Model](https://mlsanity.com/paper/2010.00114/) (2020)
- [Guided Fine-Tuning for Large-Scale Material Transfer](https://mlsanity.com/paper/2007.03059/) (2020)

## Built on by (most cited first, 25 of 25)

- [Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation](https://mlsanity.com/paper/2209.10510/) (2022)
- [ControlMat: A Controlled Generative Approach to Material Capture](https://mlsanity.com/paper/2309.01700/) (2023)
- [MatSynth: A Modern PBR Materials Dataset](https://mlsanity.com/paper/2401.06056/) (2024)
- [MatFuse: Controllable Material Generation with Diffusion Models](https://mlsanity.com/paper/2308.11408/) (2023)
- [MatFusion: A Generative Diffusion Model for SVBRDF Capture](https://mlsanity.com/paper/2406.06539/) (2024)
- [Material Palette: Extraction of Materials from a Single Image](https://mlsanity.com/paper/2311.17060/) (2023)
- [UMat: Uncertainty-Aware Single Image High Resolution Material Capture](https://mlsanity.com/paper/2305.16312/) (2023)
- [VLMaterial: Procedural Material Generation with Large Vision-Language Models](https://mlsanity.com/paper/2501.18623/) (2025)
- [MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets](https://mlsanity.com/paper/2404.13923/) (2024)
- [ReflectanceFusion: Diffusion-based text to SVBRDF Generation](https://mlsanity.com/paper/2406.14565/) (2024)
- [Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Images](https://mlsanity.com/paper/2509.09952/) (2025)
- [StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning](https://mlsanity.com/paper/2406.09293/) (2024)
- [MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis](https://mlsanity.com/paper/2511.16957/) (2025)
- [MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models](https://mlsanity.com/paper/2501.15981/) (2025)
- [FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Clothing Images](https://mlsanity.com/paper/2410.01801/) (2024)
- [Single-image Reflectance and Transmittance Estimation from Any Flatbed Scanner](https://mlsanity.com/paper/2502.14462/) (2025)
- [RETRO: REthinking Tactile Representation Learning with Material PriOrs](https://mlsanity.com/paper/2505.14319/) (2025)
- [DualMat: PBR Material Estimation via Coherent Dual-Path Diffusion](https://mlsanity.com/paper/2508.05060/) (2025)
- [Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap](https://mlsanity.com/paper/2510.23494/) (2025)
- [Diffuse Map Guiding Unsupervised Generative Adversarial Network for SVBRDF Estimation](https://mlsanity.com/paper/2205.11951/) (2022)
- [Neural Appearance Modeling From Single Images](https://mlsanity.com/paper/2406.18593/) (2024)
- [Design of an Expression Recognition Solution Based on the Global Channel-Spatial Attention Mechanism and Proportional Criterion Fusion](https://mlsanity.com/paper/2503.11935/) (2025)
- [SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation](https://mlsanity.com/paper/2508.17316/) (2025)
- [Phieat: Physically Grounded Material Feature Representation](https://mlsanity.com/paper/2511.11270/) (2025)
- [DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer](https://mlsanity.com/paper/2605.15681/) (2026)

## 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.