Critically analysing writing style of seed paper: RGB-D Tracking and Optimal Perception of Deformable Objects

I have reviewed my seed paper "RGB-D Tracking and Optimal Perception of Deformable Objects " to assess its strengths and weaknesses. Taking such a perspective has helped me in viewing the paper from a new angle, and various strengths and weaknesses of the papers core content have emerged. They are as follows:

1. Clearly structured but sometimes the transitions are not always smooth or explicitly mentioned

The paper is structured into Introduction, Method, Results, Conclusion. The method section is not explicitly mentioned which confused me slightly but overall the sections and subsections seem relevant and appropriately used. Occasionally the transitions from section to section seem not as smooth. For example end of Section II.C (Point Cloud Over-Segmentation into Supervoxels) and section III is abrupt without any transitional sentence linking them together. I think such bridge sentences can make the reading smoother. 

The paper could also use a Background section to explain in detail some of the aspects specific to 3d image segmentation

 2. Simple and concise wording but sometimes too much technical jargon

Overall, the paper is easy to read but it also contains paragraphs that are packed with too much information and technical abbreviations especially in the methods section. I think this makes it hard to understand when many technical acronyms such as SLAM, ORB-SLAM2, VCCS, LCCP etc are used in quick succession. It is dense and hard to read and follow, especially for audiences that do not have experience in the field of object tracking. Adding the full name of  acronyms such as SLAM (simultaneous localisation and mapping) in each page or at least once per section would also help keep track of the terminology.

3. Use of internal reference makes it intuitive to jump around sections

The paper contains various sections, subsections and figures and all are well connected with internal references. If the text mentions for example Fig 3, a mouse click will lead to the exact figure. For me personally, it is an intuitive way to follow the content without disruptions in reading

4. Extensive Related Works section helps me in finding new sources to build up on this paper. 

The paper contains related works on various subtopics such as deformable-object manipulation and tracking, SLAM and dense reconstruction, supervoxel segmentation etc.. Essentially, the paper uses figures to illustrate a pipeline and  summarises state-of-the-art approaches for each component in the pipeline and provides references to it. This makes it very intuitive to hand-select components that are needed and find papers regarding it. For example, this paper considers a moving camera, but in my VT project the camera is stationary-so I can focus specifically on methods that are relevant for me such as supervoxel segmentation and dive deeper into those topics using the references.

It is also missing a camera calibration step of the camera. As I need to perform this calibration, I need to find other papers that demonstrate such a internal, external and depth calibration

Overall I find the paper an excellent starting point that offers a step by step pipeline to perform image segmentation and several references for further research.