VCLab

 

RESEARCH AREAS   PEOPLE   PUBLICATIONS   COURSES   ABOUT US
Home / Publications

indicator

Computer Graphics Forum (CFG)

 
Progressive Acquisition of SVBRDF and Shape in Motion
 
 
  Hyunho Ha Seung-Hwan Baek Giljoo Nam Min H. Kim  
           
  KAIST  
           
  teaser
  (a) We provide the first-ever method to simultaneously estimate the SVBRDF, shape, and motion of dynamic objects using a single RGBD camera. (b)–(e) We obtain both diffuse and specular appearance with our novel joint optimization scheme, based on our hierarchical data structure, which allows us to render captured scenes under novel view and light conditions. Refer to the supplemental video for more results.  
     
   
  Supplemental video
   
  Abstract
   
  To estimate appearance parameters, traditional SVBRDF acquisition methods require multiple input images to be captured with various angles of light and camera, followed by a post-processing step. For this reason, subjects have been limited to static scenes, or a multiview system is required to capture dynamic objects. In this paper, we propose a simultaneous acquisition method of SVBRDF and shape allowing us to capture the material appearance of deformable objects in motion using a single RGBD camera. To do so, we progressively integrate photometric samples of surfaces in motion in a volumetric data structure with a deformation graph. Then, building upon recent advances of fusion-based methods, we estimate SVBRDF parameters in motion. We make use of a conventional RGBD camera that consists of the color and infrared cameras with active infrared illumination. The color camera is used for capturing diffuse properties, and the infrared camera-illumination module is employed for estimating specular properties by means of active illumination. Our joint optimization yields complete material appearance parameters. We demonstrate the effectiveness of our method with extensive evaluation on both synthetic and real data that include various deformable objects of specular and diffuse appearance.
   
  BibTeX
 
@Article{sBRDF-Fusion:CGF:2020,
  author  = {Hyunho Ha and Seung-Hwan Baek and Giljoo Nam and Min H. Kim},
  title   = {Progressive Acquisition of SVBRDF and Shape in Motion},
  journal = {Computer Graphics Forum},
  year    = {2020},
  volume  = {},
  number  = {},
  pages   = {},
  doi     = "",
  url     = "",
}  
   
icon
Preprint paper:
PDF (22.1MB)
icon
Preprint supplemental:
PDF (1MB)
www CGF
website
 
 

Hosted by Visual Computing Laboratory, School of Computing, KAIST.

KAIST