CN112634156A - Method for estimating material reflection parameter based on portable equipment collected image - Google Patents
Method for estimating material reflection parameter based on portable equipment collected image Download PDFInfo
- Publication number
- CN112634156A CN112634156A CN202011530944.1A CN202011530944A CN112634156A CN 112634156 A CN112634156 A CN 112634156A CN 202011530944 A CN202011530944 A CN 202011530944A CN 112634156 A CN112634156 A CN 112634156A
- Authority
- CN
- China
- Prior art keywords
- image
- ambient light
- estimating
- reflection
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000000463 material Substances 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims abstract description 8
- 238000012937 correction Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims description 2
- 238000007670 refining Methods 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 238000009877 rendering Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for estimating material reflection parameters based on images acquired by portable equipment. The method comprises the following steps: shooting a material environment light image and a flash lamp image; estimating the roughness, the specular reflection coefficient, the diffuse reflection coefficient and the normal mapping of the material according to the ambient light map; calibrating the direction, distance and real irradiance from pixel to the camera and the light source; solving a color channel correction vector between the ambient light map and the flash light map; and determining the positions of similar pixel points based on clustering, determining the final clustering class number by adopting a gradual iterative refinement mode, and endowing the points in each class with the same reflection parameters. The method can be used for conveniently estimating the SVBRDF parameters of the material, aiming at the phenomena of serious halation and the like of some material mapping images estimated by the existing neural network, the reflection parameters of the material are estimated again by shooting a material flashlight image and an environment light image, and the reality of rendering is improved.
Description
Technical Field
The invention relates to material reflection parameter estimation, in particular to a method for estimating material reflection parameters based on images acquired by portable equipment.
Background
In the real world, the appearance attributes of an object under different illumination conditions and different viewing angles are determined by the material of the surface of the object, and how to conveniently and efficiently recover the material is an important topic of computer graphics at present, and the method is widely applied to the fields of visual effect, electronic commerce, product design, entertainment and the like. However, it is still a challenging problem to obtain high quality material appearance from the real world, and the biggest challenge is to have great complexity of material appearance in the real world. In the real world, objects are generally composed of multiple materials, and the surfaces of the materials have complex geometries, which increases the difficulty of acquisition and modeling.
After the light emitted by the light source irradiates the surface of the object, a part of the light is absorbed, and the other part of the light is reflected by the surface. BRDF is defined as the point on the surface of an object at a particular wavelength along ωo：(θo，φo) Luminance L and ω of directional emissioni：(θi，φi) Ratio between directional incident light illuminance E:
although the BRDF model is capable of effectively representing the reflection characteristics of an object, its parameters do not contain position information by definition. The BRDF model is generally only suitable for representing single color objects with no fine relief on the surface, such as metal, opaque plastic, and single color cloth. However, in the real world, the material meeting such characteristics is very few, and the surfaces of many objects have slight fluctuation and color variation, and in order to describe such objects, a spatially varying brdf (svbrdf) model is proposed:
wherein p: and (x, y) represents the coordinates of the object surface point.
Therefore, SVBRDF (spatial-varying bi-directional reflection distribution function) is generally adopted to describe the reflection characteristics of the surface of the object. How to acquire and model the material SVBRDF is an important research topic, and the current research focus focuses on acquiring images by using portable devices such as mobile phones and acquiring a small amount of images to restore the reflection characteristics of the material. Deschamaitre et al, in the document (Single-image svbrdf capture with a rendering-aware deep network), "ACM Transactions on Graphics (ToG)37(4),1-15,2018, propose a method for automatically extracting and understanding visual cues such as texture, highlight and shadow by training a deep neural network, so that the appearance attributes of material can be perceived from a Single image. The method learns a series of prior and constraint by learning a large number of data sets to obtain a visually reasonable solution. However, a large number of tests show that the method is not robust, especially on a material with brightness which is a high-light material and the brightness of which changes drastically with the change of an angle, an output result has obvious artifacts on a parameter map, and sometimes, the roughness and the specular reflection coefficient are estimated and the deviation of a true value is large.
Disclosure of Invention
In order to overcome the defects, the invention provides a method for estimating the material reflection parameter based on the collected image of the portable equipment, the method takes a few pictures through the portable equipment such as a mobile phone and the like, solves the problem that the image sticking is easy to generate artifacts in the Deschaint method, and re-estimates the highlight parameter and roughness of the material, so that the recovered material image is closer to the real image. The method shoots an ambient light image and an image under a flash lamp to re-estimate the reflection parameters of the material.
The invention is realized by adopting the following technical scheme:
a method for estimating material reflection parameters based on images acquired by portable equipment is used for estimating the SVBRDF of the material by shooting a flash light image and an ambient light image, and mainly comprises the following steps:
respectively shooting a picture of the material under ambient light and a picture of the material under a flash lamp by combining an auxiliary calibration plate; inputting the environment light image into a material estimation network (such as a method for perceiving the appearance attribute of the material from a single image proposed by Deschaientre and the like) to estimate the roughness, the specular reflection coefficient, the diffuse reflection coefficient and the normal four-piece chartlet of the material; calibrating the direction, the distance and the real irradiance from the flash lamp image and the ambient light image to the camera and the light source pixel by pixel; solving a color channel correction vector between the ambient light map and the flash light map; and determining the positions of similar pixel points by a clustering-based method, determining the final clustering class number by adopting a gradual iterative refinement mode, and endowing the points in each class with the same reflection parameters.
As an improvement of the invention, a fitting method is adopted to solve the color channel correction vector between the ambient light image and the flash lamp image, and because the light fields are different, the colors of the ambient light image and the flash lamp image have obvious color cast, and the part determining the color of the image is a diffuse reflection part, therefore, a proportionality coefficient is added to three color channels of a diffuse reflection item during fitting, so that the color tone of the diffuse reflection part of the ambient light is consistent with the color tone of the diffuse reflection part of the flash lamp image.
As another improvement of the invention, the clustering category is determined by adopting a gradual iterative refinement mode. Initially, the classes in the image are divided into fewer classes (e.g., k ═ 3: 10), and then the refinement is iterated step by step, and the parent result is used as the initial value of the subclass until the condition for continued subdivision is no longer satisfied.
The invention has the beneficial effects that:
the color channel correction vector between the ambient light image and the flash lamp image is solved by adopting a fitting method, so that the tone of the diffuse reflection part of the ambient light is consistent with that of the diffuse reflection part of the flash lamp image, and the effect of white balance of the image is achieved; the clustering method of gradual iterative refinement is adopted to determine the pixel category number in the image, balance is carried out between the detail sense of the image and the fitting robustness, and the problem that the clustering number of the problems is difficult to determine in the existing method is solved. Compared with the SVBRDF which estimates the material based on the neural network method, the method can avoid the generation of artifacts caused by flash lamp light spots in the Deschaint method, and estimates more reasonable specular reflection coefficient and roughness, so that the material rendering result is closer to the real result.
Drawings
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings;
FIG. 1 is a flow chart of the present invention for estimating material reflectance parameters based on a small number of images acquired by a portable device;
FIG. 2 is a picture of 4 materials collected by the present invention taken under ambient light and a flash lamp, respectively;
FIG. 3 is a comparison of normal, diffuse reflectance, roughness and high gloss maps recovered from 4 materials using the present invention and prior art methods.
FIG. 4 is a graph comparing the results of the present invention and the prior art method in 4 materials rendered under the same light source.
Detailed Description
As shown in fig. 1, the present invention provides a method for estimating material reflection parameters based on a small number of images collected by a portable device, which comprises the following steps:
1. and (5) shooting a material environment light image and a flash lamp image.
1.1 shooting in a camera RAW image mode, and ensuring that the image is not subjected to nonlinear transformation of an ISP flow.
1.2 placing auxiliary calibration paper in the area of the material to be collected, and shooting an image under ambient light and recording the image as I1. Keeping the position of the auxiliary calibration paper unchanged, keeping the flash lamp of the mobile phone on, and taking an image as I2When shooting, the distance between the mobile phone and the material is as short as possible, so that the angle change range is large.
2. And inputting the ambient light map into a material estimation network to estimate roughness, a specular reflection coefficient, a diffuse reflection coefficient and a normal mapping of the material.
Imaging ambient light I1Inputting the data into a network proposed in the documents Deschaint, Valentin, et al, "Single-image svbrdf capture with a rendering-aware deep network," ACM Transactions on Graphics (ToG)37(4),1-15,2018 ", to obtain a diffuse reflection map, a roughness map, a highlight map and a normal map, which are respectively marked as rhod、α、ρsAnd n.Wherein the diffuse reflection map ρdThe normal mapping n is close to the true value, and the two mappings are taken as the final result to psAnd alpha is re-estimated.
3. The direction, distance and true irradiance to the camera and light source are calibrated pixel by pixel.
Calibrating a camera response curve f of a mobile phone for estimating an image I1And I2Corresponding true irradiance E1And E2The mapping relation between the ambient light intensity and the exposure time of the camera to the image pixel brightness is as follows:
I＝f(X)＝f(EΔt)
for each pixel point on the image, E represents irradiance irradiating the pixel point in unit time, namely ambient light intensity, X represents total energy received by the pixel point in exposure time delta t, and the luminosity response function f represents nonlinear mapping from X to pixel point brightness I. f is invertible, and the inverse function is defined as:
g(I)＝lnf-1＝ln(E)+ln(Δt)
and calibrating the field angle FOV of the mobile phone, and estimating the direction l and the distance d from each pixel point in the image to the light source and the direction v from each pixel point to the camera. Since the flash may not fall exactly in the center of the image, the centroid of the top 5% brightest point on the image is chosen as the XY origin of the flash.
4. And solving a color channel correction vector between the ambient light map and the flash light map.
Because of the difference of light fields, the colors of an ambient light image and a flash light image have obvious color cast, and the part determining the color of the image is a diffuse reflection part, proportional coefficients are added to three color channels of a diffuse reflection term during fitting, and a fitting formula is as follows:
wherein, [ r, g, b [ ]]To control color channel scale vectors; r is2Is the distance of the pixel to the light source; l isrIrradiance, L, received for the cameraiFor irradiation by light sourceAnd (4) degree.
In the flashlight view, ambient light is not explicitly modeled, but is implicitly integrated into the SVBRDF model.
Assuming that the roughness and specular reflection coefficient of all points in the whole image are consistent, all points in the image are used for fitting the channel coefficients [ r, g, b ], and the Levenberg-Marquarerl algorithm is adopted in the solving process.
5. And determining the positions of similar pixel points by a clustering-based method and determining the final clustering class number by adopting gradual iterative refinement.
5.1 the clustering method is used for judging the positions of the similar points. Map I of ambient light1As a reference image for determining the pixel point category, in order to better measure the distance of the color, the picture is transferred from the RGB color space to the CIE 1976L a b color space.
And 5.2, a K-means clustering mode is used, a centroid initialization mode is K-means + +, and a clustering acceleration algorithm based on a triangle inequality is used for improving the operation speed.
5.3 determining the cluster category. Initially, the classes in the image are classified into fewer classes k ═ 3: 10], then gradually iterating and taking the parent class result as the initial value of the subclass until the condition of continuing subdivision is not met any more, and assigning the same reflection parameter to the point in each class. The requirements that may continue to subdivide needs are:
Ni＞λ1·(w·h)，λ1∈(0.05，0.2)
Di＞λ2·min(w，h)，λ2∈(0.2，0.5)
wherein N isiIndicates the number of pixels in the ith cluster, DiRepresents the average distance from each point in the ith cluster to the position of the spatial distribution centroid of all the points in the cluster, w and h are the width and height of the image, respectively, and lambda1And λ2Is a control coefficient.
Example 1
This example mainly compares the estimation results of the existing method (see, specifically, "Single-image svbrdf capture with a rendering-aware deep network," ACM transformations on Graphics (ToG)37(4),1-15,2018 ]) and the method of the present invention in real materials. Fig. 2 is a picture of 4 materials taken under ambient light and a flash light. Fig. 3 is a comparison between the present invention and the existing method, and it can be found that the method of the present invention has no artifact phenomenon commonly existing in the existing method, and the highlight map and the roughness map estimated by the method are more objective and practical, and from the rendering result of fig. 4, the image re-rendered by the method is closer to the actually acquired image than the existing method.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (3)
1. A method for estimating material reflection parameters based on images acquired by a portable device is characterized in that SVBRDF of the material is estimated by shooting a flashlight image and an ambient light image, and the method comprises the following steps:
(1) estimating the roughness, the specular reflection coefficient, the diffuse reflection coefficient and the normal mapping of the material according to the ambient light map; calibrating the direction, the distance and the real irradiance from the flash lamp image and the ambient light image to the camera and the light source pixel by pixel;
(2) solving a color channel correction vector between the ambient light map and the flash lamp map;
(3) and determining the positions of similar pixel points by a clustering-based method, determining the final cluster number by adopting a gradual iterative refinement mode, and endowing the points in each cluster with the same reflection parameters.
2. The method for estimating material reflection parameters based on portable device captured images according to claim 1, wherein the step (2) comprises: and solving the color channel correction vector between the ambient light image and the flash lamp image by adopting a fitting method, and adding parameters for controlling proportion to the three color channels of the diffuse reflection item in the fitting process so as to keep the tone of the diffuse reflection part of the ambient light image consistent with the tone of the diffuse reflection part of the flash lamp image.
3. The method for estimating material reflection parameters based on images acquired by a portable device according to claim 1, wherein the step (3) is specifically as follows: initially, only classifying the categories of pixel points in the image into a few categories, then gradually iterating and refining, taking the result of the parent category as the initial value of the subclass until the condition of continuous subdivision is not met, and endowing the points in each category with the same reflection parameters;
the conditions for continuous subdivision are as follows:
Ni＞λ1·(w·h)，λ1∈(0.05，0.2)
Di＞λ2·min(w，h)，λ2∈(0.2，0.5)
wherein N isiIndicates the number of pixels in the ith cluster, DiRepresents the average distance from each point in the ith cluster to the position of the spatial distribution centroid of all the points in the cluster, w and h are the width and height of the image, respectively, and lambda1And λ2Is a control coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011530944.1A CN112634156B (en) | 2020-12-22 | 2020-12-22 | A method for estimating material reflection parameters based on images captured by portable devices |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011530944.1A CN112634156B (en) | 2020-12-22 | 2020-12-22 | A method for estimating material reflection parameters based on images captured by portable devices |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112634156A true CN112634156A (en) | 2021-04-09 |
| CN112634156B CN112634156B (en) | 2022-06-24 |
Family
ID=75321016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011530944.1A Active CN112634156B (en) | 2020-12-22 | 2020-12-22 | A method for estimating material reflection parameters based on images captured by portable devices |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112634156B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119779A (en) * | 2021-10-29 | 2022-03-01 | 浙江凌迪数字科技有限公司 | Method for generating material map through multi-angle polishing shooting and electronic device |
| CN114677292A (en) * | 2022-03-07 | 2022-06-28 | 北京航空航天大学 | High-resolution material recovery method based on two image inverse rendering neural network |
| CN114842121A (en) * | 2022-06-30 | 2022-08-02 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for generating mapping model training and mapping |
| CN114926593A (en) * | 2022-06-13 | 2022-08-19 | 山东大学 | SVBRDF material modeling method and system based on single highlight image |
| CN115035306A (en) * | 2022-06-24 | 2022-09-09 | Oppo广东移动通信有限公司 | Image material determination method and related device |
| CN115375847A (en) * | 2022-08-25 | 2022-11-22 | 北京百度网讯科技有限公司 | Material recovery method, three-dimensional model generation method and model training method |
| CN116940827A (en) * | 2022-02-23 | 2023-10-24 | 卡尔蔡司光学国际有限公司 | Computer-implemented method, computer program, data processing system and device for determining a reflection behaviour of a surface of an object, and storage medium having stored thereon instructions for determining a reflection behaviour of a surface of an object |
| WO2023158374A3 (en) * | 2022-02-21 | 2023-11-30 | 脸萌有限公司 | Subject material determination method and apparatus, and electronic device and storage medium |
| CN117252776A (en) * | 2023-09-26 | 2023-12-19 | 钛玛科（北京）工业科技有限公司 | Image adjustment method, device and equipment suitable for multiple materials |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117488A (en) * | 2011-02-21 | 2011-07-06 | 北京航空航天大学 | Method for constructing surface reflection characteristics of real object in virtual environment |
| CN106331663A (en) * | 2016-08-26 | 2017-01-11 | 珠海金山网络游戏科技有限公司 | System and method for acquiring interactive materials for portable devices |
| WO2018152422A1 (en) * | 2017-02-16 | 2018-08-23 | Essenlix Corporation | Assay with textured surface |
| US20190333266A1 (en) * | 2018-04-30 | 2019-10-31 | The Regents Of The University Of California | Methods and systems for acquiring svbrdf measurements |
-
2020
- 2020-12-22 CN CN202011530944.1A patent/CN112634156B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117488A (en) * | 2011-02-21 | 2011-07-06 | 北京航空航天大学 | Method for constructing surface reflection characteristics of real object in virtual environment |
| CN106331663A (en) * | 2016-08-26 | 2017-01-11 | 珠海金山网络游戏科技有限公司 | System and method for acquiring interactive materials for portable devices |
| WO2018152422A1 (en) * | 2017-02-16 | 2018-08-23 | Essenlix Corporation | Assay with textured surface |
| US20190333266A1 (en) * | 2018-04-30 | 2019-10-31 | The Regents Of The University Of California | Methods and systems for acquiring svbrdf measurements |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119779A (en) * | 2021-10-29 | 2022-03-01 | 浙江凌迪数字科技有限公司 | Method for generating material map through multi-angle polishing shooting and electronic device |
| WO2023158374A3 (en) * | 2022-02-21 | 2023-11-30 | 脸萌有限公司 | Subject material determination method and apparatus, and electronic device and storage medium |
| CN116940827A (en) * | 2022-02-23 | 2023-10-24 | 卡尔蔡司光学国际有限公司 | Computer-implemented method, computer program, data processing system and device for determining a reflection behaviour of a surface of an object, and storage medium having stored thereon instructions for determining a reflection behaviour of a surface of an object |
| CN114677292B (en) * | 2022-03-07 | 2022-11-01 | 北京航空航天大学 | High-resolution material restoration method based on two-image inverse rendering neural network |
| CN114677292A (en) * | 2022-03-07 | 2022-06-28 | 北京航空航天大学 | High-resolution material recovery method based on two image inverse rendering neural network |
| CN114926593A (en) * | 2022-06-13 | 2022-08-19 | 山东大学 | SVBRDF material modeling method and system based on single highlight image |
| CN114926593B (en) * | 2022-06-13 | 2024-07-19 | 山东大学 | SVBRDF material modeling method and system based on Shan Zhanggao light images |
| CN115035306A (en) * | 2022-06-24 | 2022-09-09 | Oppo广东移动通信有限公司 | Image material determination method and related device |
| CN114842121B (en) * | 2022-06-30 | 2022-09-09 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for generating mapping model training and mapping |
| CN114842121A (en) * | 2022-06-30 | 2022-08-02 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for generating mapping model training and mapping |
| CN115375847A (en) * | 2022-08-25 | 2022-11-22 | 北京百度网讯科技有限公司 | Material recovery method, three-dimensional model generation method and model training method |
| CN115375847B (en) * | 2022-08-25 | 2023-08-29 | 北京百度网讯科技有限公司 | Material recovery method, three-dimensional model generation method and model training method |
| CN117252776A (en) * | 2023-09-26 | 2023-12-19 | 钛玛科（北京）工业科技有限公司 | Image adjustment method, device and equipment suitable for multiple materials |
| CN117252776B (en) * | 2023-09-26 | 2024-04-30 | 钛玛科（北京）工业科技有限公司 | Image adjustment method, device and equipment suitable for multiple materials |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112634156B (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112634156A (en) | Method for estimating material reflection parameter based on portable equipment collected image | |
| Faridul et al. | Colour mapping: A review of recent methods, extensions and applications | |
| CN114174783B (en) | Systems and methods for creating topical formulations with improved image capture | |
| US8787666B2 (en) | Color analytics for a digital image | |
| Matusik et al. | Progressively-Refined Reflectance Functions from natural Illumination. | |
| Drew et al. | Robust estimation of surface properties and interpolation of shadow/specularity components | |
| US8249342B1 (en) | Color analytics for a digital image | |
| CN103839236A (en) | Image white balance method based on sparse representation | |
| US9418434B2 (en) | Method for detecting 3D geometric boundaries in images of scenes subject to varying lighting | |
| Ciortan et al. | A practical reflectance transformation imaging pipeline for surface characterization in cultural heritage | |
| Han et al. | Automatic illumination and color compensation using mean shift and sigma filter | |
| JP7633790B2 (en) | Texture acquisition system, texture acquisition device, and texture acquisition program | |
| Schindler | Photometric stereo via computer screen lighting for real-time surface reconstruction | |
| Caleiro et al. | Color-spaces and color segmentation for real-time object recognition in robotic applications | |
| Boss et al. | Single image brdf parameter estimation with a conditional adversarial network | |
| JP3825383B2 (en) | 3D shape measuring method and 3D shape measuring apparatus | |
| Robles-Kelly et al. | Estimating the surface radiance function from single images | |
| Miyagawa et al. | radiometric compensation using color-mixing matrix reformed from light transport matrix | |
| Dror et al. | Surface reflectance estimation and natural illumination statistics | |
| Clark | Photometric stereo with nearby planar distributed illuminants | |
| Kasper et al. | Multiple point light estimation from low-quality 3D reconstructions | |
| JP5050141B2 (en) | Color image exposure evaluation method | |
| JP4359662B2 (en) | Color image exposure compensation method | |
| Bokaris et al. | One-frame delay for dynamic photometric compensation in a projector-camera system | |
| MacDonald | Visual realism in digital heritage |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |