Table of Contents
Technical Challenges
Hardware
Acquisition and reconstruction
Results
Outlook
Home Technology peripherals AI OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Nov 26, 2023 pm 05:26 PM
database ai

In the field of computational graphics, the appearance of a material describes the complex physical interactions between real objects and light. This description is often called a Spatially-Varying Bidirectional Reflectance Distribution Function (SVBRDF). It is an integral component in visual computing and has been widely used in fields such as cultural heritage, e-commerce, video games, and visual effects

over the past two decades , especially after deep learning became popular, the demand for high-precision and diverse digital material appearances in academia and industry has continued to increase. However, due to technical challenges, collecting large-scale databases is still a very difficult task. Currently, the number of publicly available material appearance real-shot databases is very limited

For this reason, Zhejiang University The research team from the National Key Laboratory of Computer-Aided Design and Graphics Systems and Hangzhou Xiangxin Technology Co., Ltd. jointly proposed a new integrated system for robust, high-quality and efficient acquisition of planar anisotropic material appearance. Using this system, the research team built the OpenSVBRDF public material database.

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

The following is a display of some material samples in the OpenSVBRDF database, as shown in Figure 1. Each row belongs to the same material category

This is the first large-scale measured database of 6-dimensional SVBRDF, with a total of 1,000 high-quality plane samples and a spatial resolution of 1,024×1,024. Equivalent to more than 1 billion measured BRDF, covering 9 categories including wood, fabric and metal.

Database home page: https://opensvbrdf.github.io/

Currently, the database is completely free for non-commercial applications. You only need to submit basic information on the website to apply for an account. After review, you can directly download relevant data and codes including GGX texture maps. The related research paper "OpenSVBRDF: A database containing measured spatially varying reflectivity" has been accepted by the top international conference on computer graphics ACM SIGGRAPH ASIA 2023 (journal paper)

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Please click the following link to view the paper homepage: https://svbrdf.github.io/

Technical Challenges

If the original meaning is changed, the content that needs to be rewritten is: According to [Lawrence et al. 2006], the direct sampling method is to make dense measurements of the physical material under different lighting and viewing angles. Although this method can obtain high-quality and stable acquisition results, it is less efficient and requires a lot of time and storage costs. Another option is a prior knowledge-based reconstruction method, which can reconstruct materials from sparse sampled data. Although this method improves efficiency, the quality of reconstruction may be unsatisfactory when the prior conditions are not met [Nam et al. 2018]. In addition, although the current optical path multiplexing technology has achieved high acquisition efficiency and reconstruction quality, the robustness of the algorithm still needs to be improved in processing highly complex materials, such as brushed metal and polished veneer [Kang et al. 2018]

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Figure 2: Representative work of existing material collection research. From left to right they are [Lawrence et al. 2006], [Nam et al. 2018] and [Kang et al. 2018]. Among them [Kang et al. 2018] is the team's early work published in ACM SIGGRAPH in 2018.

Hardware

In order to efficiently scan the material appearance, the research team built a near-half-cube near-field illumination multiplexing device. The size is approximately 70cm×70cm×40cm. The sample is placed on a clear acrylic plate and can be quickly slid in/out via drawer slides to achieve high throughput rates. The device consists of 2 machine vision cameras and 16,384 high-brightness LEDs. The two cameras capture samples from angles of approximately 90 degrees (primary viewing angle) and 45 degrees (secondary viewing angle). The LEDs are distributed on 6 sides of the device. The self-developed high-performance control circuit is responsible for independent brightness control of each LED and achieves high-precision synchronization of light source projection and camera exposure at the hardware level.

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Please see Figure 3: The appearance of the acquisition equipment and the photos taken from two different angles

Acquisition and reconstruction

This system uniquely combines two currently popular methods, network-based prediction and fine-tuning, to improve the efficiency of physical acquisition. Optimization of differentiable lighting patterns while further improving the quality of results through fine-tuning. This is the first time to achieve high robustness, high quality and high efficiency of acquisition and reconstruction of planar SVBRDF

Specifically, in order to reconstruct the physical sample, the researchers first achieved this by Match dense SIFT features to establish high-precision correspondence between two camera views. For physical acquisition, the lighting pattern is first optimized as part of an autoencoder to achieve efficient acquisition. The autoencoder automatically learns how to reconstruct complex appearances based on measurements from two views and represents the results as intermediate neural representations. Subsequently, the neural expressions were fine-tuned by plotting image errors to improve the quality and robustness of the final results, based on photos taken by a principal-view camera under 63 equivalent linear light sources. Figure 3 shows the processing flow of the entire system. For details, please refer to the original paper

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Figure 4: Acquisition and reconstruction process of the entire system.

Results

The research team collected appearance data and collected a total of 1,000 samples divided into 9 categories. To make it easier to use the physics-based rendering pipeline (PBR), the study also adapted neural expressions to industry-standard anisotropic GGX BRDF model parameters. Figure 5 shows the sub-parameters and properties of the material reconstruction results. Each sample contains 193 original HDR photos (total size 15GB), intermediate neural expressions (290MB), and 6 maps, including texture maps and transparency maps representing GGX parameters (total size 55MB). The spatial resolution of both neural expressions and texture maps is 1,024×1,024

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

After rewriting: Figure 5: Breakdown of reconstructed material results Properties (including neural expression, diffuse reflectance, specular reflectance, roughness, etc.)

In order to prove the correctness of the reconstruction results, the researchers took the photos from the main perspective (the picture below) First row) and neural expression mapping results (second row below) are compared. Quantitative errors (expressed as SSIM/PSNR) are noted at the bottom of the plot. As can be seen from the results in the figure below, this system achieves high-quality material reconstruction (SSIM>=0.97, PSNR>=34db).

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Figure 6: Comparison of real photos and neural expression rendering results from the main perspective.

In order to further prove the generalization of the reconstruction results in the viewing angle domain, the researchers compared the photos taken from two viewing angles under the illumination of a point light source and the results drawn using GGX fitting parameters. The comparison verifies the cross-view correctness of the reconstruction results.

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Picture 7: Comparison of actual photos taken and results drawn using anisotropic GGX fitting parameters in two viewing angles

The researchers also demonstrated the application of the database in three aspects: material generation, material classification and material reconstruction. Please refer to the original paper for specific details.

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Figure 8 shows the process of using OpenSVBRDF to train MaterialGAN to achieve material generation and interpolation

OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Figure 9 shows the process of using OpenSVBRDF to train active lighting to improve material classification accuracy


OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world

Rewritten content is as follows: Picture 10: Using OpenSVBRDF to improve the quality of BRDF reconstruction based on single-point sampling (left) and optical path multiplexing (right)

Outlook

Researchers will work hard to expand the existing database and add material samples showing diverse appearances. In the future, they also plan to build a large-scale, high-precision measured object database that includes both material appearance and geometric shape. In addition, researchers will design a public benchmark in the direction of material estimation, classification and generation based on OpenSVBRDF, and provide solid data guarantee to promote the future development of related research through objective and quantitative standard testing.

The above is the detailed content of OpenSVBRDF released: a large-scale 6-dimensional material real-shot database at the ImageNet level in the material world. For more information, please follow other related articles on the PHP Chinese website!

Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Article

Repo: How To Revive Teammates
1 months ago By 尊渡假赌尊渡假赌尊渡假赌
R.E.P.O. Energy Crystals Explained and What They Do (Yellow Crystal)
2 weeks ago By 尊渡假赌尊渡假赌尊渡假赌
Hello Kitty Island Adventure: How To Get Giant Seeds
1 months ago By 尊渡假赌尊渡假赌尊渡假赌

Hot Tools

Notepad++7.3.1

Notepad++7.3.1

Easy-to-use and free code editor

SublimeText3 Chinese version

SublimeText3 Chinese version

Chinese version, very easy to use

Zend Studio 13.0.1

Zend Studio 13.0.1

Powerful PHP integrated development environment

Dreamweaver CS6

Dreamweaver CS6

Visual web development tools

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)

C language starts from 0 C language starts from 0 Apr 03, 2025 pm 08:24 PM

It may be a bit difficult to get started with C language learning, but after mastering the correct method, you will quickly master the basics and gradually master them. This guide will guide you step by step to learn the core concepts of C language, from basics to advanced topics. Directory C language basics and data types User input conditional expression abbreviation switch statement C language array nested loop C language function structure pointer C language basics and data types C programs follow standard structures and use multiple data types to define variables. The basic program structure is as follows: #includeintmain(){printf("hello,world!");ret

What are the types of return values ​​of c language function? Summary of types of return values ​​of c language function? What are the types of return values ​​of c language function? Summary of types of return values ​​of c language function? Apr 03, 2025 pm 11:18 PM

The return value types of C language function include int, float, double, char, void and pointer types. int is used to return integers, float and double are used to return floats, and char returns characters. void means that the function does not return any value. The pointer type returns the memory address, be careful to avoid memory leakage.结构体或联合体可返回多个相关数据。

Concept of c language function Concept of c language function Apr 03, 2025 pm 10:09 PM

C language functions are reusable code blocks. They receive input, perform operations, and return results, which modularly improves reusability and reduces complexity. The internal mechanism of the function includes parameter passing, function execution, and return values. The entire process involves optimization such as function inline. A good function is written following the principle of single responsibility, small number of parameters, naming specifications, and error handling. Pointers combined with functions can achieve more powerful functions, such as modifying external variable values. Function pointers pass functions as parameters or store addresses, and are used to implement dynamic calls to functions. Understanding function features and techniques is the key to writing efficient, maintainable, and easy to understand C programs.

C Programmer &#s Undefined Behavior Guide C Programmer &#s Undefined Behavior Guide Apr 03, 2025 pm 07:57 PM

Exploring Undefined Behaviors in C Programming: A Detailed Guide This article introduces an e-book on Undefined Behaviors in C Programming, a total of 12 chapters covering some of the most difficult and lesser-known aspects of C Programming. This book is not an introductory textbook for C language, but is aimed at readers familiar with C language programming, and explores in-depth various situations and potential consequences of undefined behaviors. Author DmitrySviridkin, editor Andrey Karpov. After six months of careful preparation, this e-book finally met with readers. Printed versions will also be launched in the future. This book was originally planned to include 11 chapters, but during the creation process, the content was continuously enriched and finally expanded to 12 chapters - this itself is a classic array out-of-bounds case, and it can be said to be every C programmer

How to calculate c-subscript 3 subscript 5 c-subscript 3 subscript 5 algorithm tutorial How to calculate c-subscript 3 subscript 5 c-subscript 3 subscript 5 algorithm tutorial Apr 03, 2025 pm 10:33 PM

The calculation of C35 is essentially combinatorial mathematics, representing the number of combinations selected from 3 of 5 elements. The calculation formula is C53 = 5! / (3! * 2!), which can be directly calculated by loops to improve efficiency and avoid overflow. In addition, understanding the nature of combinations and mastering efficient calculation methods is crucial to solving many problems in the fields of probability statistics, cryptography, algorithm design, etc.

Unique shared library issues Unique shared library issues Apr 03, 2025 pm 08:00 PM

Problem Description Recently, I encountered a link error when I tried to link a self-built C language shared library to a local project, and I encountered a link error, prompting "Undefined reference". The error message is as follows: /bin/ld:/tmp/cchb7mj8.o:infunction`sdl_main':main.c:(.text 0x3c):undefinedreferenceto`sdl_enterappmaincallbacks'...(other similar undefined references)..collect2:error:ldreturned1exitstatusmake:***[

Exercise C: Building a simple phonebook application Exercise C: Building a simple phonebook application Apr 03, 2025 pm 08:15 PM

One of the best ways to learn C language programming is to practice it. This article will take you step through a project I recently completed: a simple phonebook application. This app demonstrates file processing and basic data management in C, allowing you to add, view, and delete contacts. The following is the complete code: #include#include//Function declaration voidaddcontact(charname[],charnumber[]);voidviewcontacts();voiddeletecontact(c

Object-oriented in C? Implementing interfaces from scratch Object-oriented in C? Implementing interfaces from scratch Apr 03, 2025 pm 08:21 PM

This article discusses how to simulate the concept of interfaces in object-oriented programming in C language. We will take the calculation of vehicle prices as an example, implement them in Java and C languages ​​respectively, compare the differences between the two languages, and show how to implement the basic functions of the interface in C. Java implementation: In Java, the interface is defined using the interface keyword, and the class implements the interface through the implements keyword. The sample code is as follows: interfaceVehicle{intprice();}classCarimplementsVehicle{privatefinalintspeed;publi

See all articles