Name of Reviewer ------------------ Colin Zheng Key Contribution ------------------ Summarize the paper's main contribution(s). Address yourself to both the class and to the authors, both of whom should be able to agree with your summary. This paper presents a novel algorithm for calibrated multi-view stereopsis that outputs a (quasi) dense set of rectangular patches covering the surfaces visible in the input images. This algorithm does not require any initialization in the form of a bounding volume, and it detects and discards automatically outliers and obstacles. It does not perform any smoothing across nearby features, yet is currently the top performer in terms of both coverage and accuracy in a number of benchmarking datasets. Novelty -------- Does this paper describe novel work? If you deem the paper to lack novelty please cite explicitly the published prior work which supports your claim. Citations should be sufficient to locate the paper and page unambiguously. Do not cite entire textbooks without a page reference. The novelty is on its match, expand, and filter procedure, which requires no smoothing or initialization, yet produces top quality results. Reference to prior work ----------------------- Please cite explicitly any prior work which the paper should cite. I'm not aware of any. Clarity ------- Does it set out the motivation for the work, relationship to previous work, details of the theory and methods, experimental results and conclusions as well as can be expected in the limited space available? Can the paper be read and understood by a competent graduate student? Are terms defined before they are used? Is appropriate citation made for techniques used? Yes. Technical Correctness --------------------- You should be able to follow each derivation in most papers. If there are certain steps which make overly large leaps, be specific here about which ones you had to skip. It's a very well written paper that I follow quite well. Experimental Validation ----------------------- For experimental papers, how convinced are you that the main parameters of the algorithms under test have been exercised? Does the test set exercise the failure modes of the algorithm? For theoretical papers, have worked examples been used to sanity-check theorems? Speak about both positive and negative aspects of the paper's evaluation. Overall Evaluation ------------------ I consider this paper more like a system paper in which the procedure shines. Every single technical component is not new by itself, yet the results look amazingly good. It's interesting that this paper uses regular grid as patches, yet still yields very good results. I would expect a color-based segmentation algorithm would outperform a grid-based method, which I would love to see it coming. Questions and Issues for Discussion ----------------------------------- What questions and issues are raised by this paper? What issues do you think this paper does not address well? How can the work in this paper be extended? I'm more interested in exploring the limitations, especially when constant-intensity assumption breaks. Is the simple occlusion reasoning algorithm described in the paper good enough? If not, how to improve?