Research

My research interests:
3D Television and Free-viewpoint TV is my major research area in PhD mainly focussing on efficient multiview coding and virtual view synthesis. Other than 3DTV, I research in Image Inpainting, Composition, Morphing and Image Retrieval. Some of the major projects are described below.

3DTV - FTV

During the last couple of decades 3DTV has gained a lot of popularity due to its quality of experience achieved through stereoscope and autostereoscopy. The depth sensation in television is achieved by rendering two or more views simultaneously that in some techniques requires special glasses too. It is desirable to use as few views as possible to achieve 3D vision that poses new challenges for coding multi-views and generating virtual views from available views.

Publications:

- 3D Video Coding

• Panorama view with spatiotemporal occlusion compensation for 3D video coding
• A panoramic 3D video coding with directional depth aided inpainting

- 3D View Synthesis & Visual Quality Enhancement

• Edge enhancement of depth based rendered image
• Depth Image Based Rendering with Inverse Mapping (VSIM)
• Edges shape enforcement for visual enhancement of depth image based rendering

- 3D Quality Assessment

• Synthesized Image Quality Evaluator (SIQE)
• Blind Depth Quality Metric (BDQM)
• DIBR-Synthesized image Quality Metric (DSQM)
• Synthesized Image Quality Metric (SIQM)

  Image Inpainting

  Image inpainting is removal of unwanted objects from digital images. The missing information in unwanted region is filled using the information from the neighborhood regions of the image. Inpainting is used in many research areas as postprocessing step in addition to recreational photography. For example, it is used to fill the holes in a novel view generated from a set of available views in Free-view TV.

   

  Publications:

  • Image inpainting based on pyramids

  • Image inpainting using dynamic weighted kernels

  • Image inpainting using cubic hermit spline

   

  Image Retrieval

  Searching an image or searching similar images to a given image from a digital image repository is important in many applications e.g., security, medicine and defense. Content Based Image Retrieval (CBIR) uses color, texture and shapes in the images to find the best matches.

   

  Publications:

  Content Based Image Retrieval Using Localized Multi-texton Histogram

  Download [bib, Paper, Source Code]

   

  Image De-fencing

  Detection and removal of fences from digital images becomes essential when an important part of the scene turns to be occluded by such unwanted structures. Image de-fencing is challenging because manually marking fence boundaries is tedious and time consuming. The fence is a distributed object and may cover a significant portion of the scene.

   

  Publications:

  Image De-fencing Framework with Hybrid Inpainting Algorithm

  Download [ Paper, Source Code]