Call for Papers: Special Issue on Physics-Based Vision meets Deep Learning

Guest Editors: 

  • Shaodi You, Assistant Professor, University of Amsterdam, Netherlands
  • Yu Li, Senior Research Scientist, Tencent, China; Research Affiliate, University of Illinois at Urbana-Champaign (UIUC) Coordinated Science Laboratory, US
  • Ying Fu, Professor, Beijing Institute of Technology, China
  • Boxin Shi, Assistant Professor & Research Professor, Peking University, China
  • Rei Kawakami, Specially Appointed Associate Professor, Tokyo Institute of Technology/ Senior Researcher, Denso IT Laboratory, Japan
  • Robby T. Tan, Associate Professor Yale-NUS College / National University of Singapore, Singapore
  • Hiroshi Kawasaki, Professor, Kyushu University, Japan

Light traveling in the 3D world interacts with the scene through intricate processes before being captured by a camera. These processes result in the dazzling effects like color and shading, complex surface and material appearance, different weathering, just to name a few. Physics based vision aims to invert the processes to recover the scene properties, such as shape, reflectance, light distribution, medium properties, etc., from the images by modelling and analyzing the imaging process to extract desired features or information.

There are many popular topics in physics-based vision. Some examples are shape from shading, photometric stereo, reflectance modelling, reflection separation, radiometric calibration, intrinsic image decomposition, and so on. As a series of classic and fundamental problems in computer vision, physics based vision facilitates high-level computer vision problems from various aspects. For example, the estimated surface normal is a useful cue for 3D scene understanding; the specular-free image could significantly increase the accuracy of image recognition problem; the intrinsic images reflecting inherent properties of the objects in the scene substantially benefit other computer vision algorithms, such as segmentation, recognition; reflectance analysis serves as the fundamental support for material classification; and, bad weather visibility enhancement is important for outdoor vision systems. In addition, this year we will expand the research topic to active lighting techniques, such as, structured light, Bidirectional Reflectance Distribution Function (BRDF) measurement and analysis, Time Of Flight (TOF) or Non line of sight imaging (NLOS), since those techniques are actual system/application of physics based vision and become more important recently.

In recent years, deep neural networks and learning techniques show promising improvement for various high-level vision tasks, such as detection, classification, tracking, image generation and synthesis, etc. With the physics imaging formation model involved, successful examples can also be found in various physics based vision problems (please refer to the references section).

When physics based vision meets deep learning, there will be mutual benefits. On one hand, classic physics based vision tasks can be implemented in a data-fashion way to handle complex scenes. This is because, a physically more accurate optical model can be too complex as an inverse problem for computer vision algorithms (usually too many unknown parameters in one model), however, it can be well approximated providing a sufficient collection of data. Later, the intrinsic physical properties are likely to be learned through a deep neural network model. Existing research has already exploited such benefit on luminance transfer, computational stereo, haze removal, differential renderer, etc.

On the other hand, high-level vision task can also be benefitted by awareness of the physics principles. For instance, physics principles can be utilized to supervise the learning process, by explicitly extracting the low-level physical principles rather than learning it implicitly. In this way, the network could be more accurate more efficient. Such physics principles have already presented the benefits in semantic segmentation, object detection, etc.

Therefore, we believe when physics based vision meets deep learning both low level and high level vision task can get the benefits. Furthermore, we believe that there are many computer vision tasks that can be tackled by solving both physics based vision and high level vision in a joint fashion to get more robust and accurate results which cannot be achieved by ignoring each side.

The topics of this special issue include, but are not limited to: Deep learning +

  • Photometric based 3D reconstruction
  • Radiometric modeling/calibration of cameras
  • Color constancy
  • Illumination analysis and estimation
  • Reflectance modeling, fitting, and analysis
  • Forward/inverse renderings
  • Material recognition and classification
  • Transparency and multi-layer imaging
  • Reflection removal
  • Intrinsic image decomposition
  • Light field imaging
  • Multispectral/hyperspectral capture, modeling and analysis
  • Vision in bad weather (dehaze, derain, etc.)
  • Structured light techniques (sensors, BRDF measurement and analysis)TOF sensors and its applications
  • Neuromorphic (event/spike) cameras
  • Differential render and its applications

Important Dates

  • Submission deadline: Dec 31, 2021
  • First review notification (tentative): March 30, 2022
  • Revision due: May 30, 2022
  • Final decision: June 30, 2021

Submission guidelines:

Submitted papers should present original, unpublished work, relevant to one of the topics of the Special Issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least three independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process. Manuscripts will be subject to a peer reviewing process and must conform to the author guide lines available on the IJCV website at: .

Please select "Physics-Based Vision meets Deep Learning" at the beginning of the submission process.

Author Resources

Authors are encouraged to submit high-quality, original work that has neither appeared in, nor is under consideration by other journals.  

All papers will be reviewed following standard reviewing procedures for the Journal. 

Papers must be prepared in accordance with the Journal guidelines:

Springer provides a host of information about publishing in a Springer Journal on our Journal Author Resources page, including  FAQs,  Tutorials  along with  Help and Support.

Other links include: