Description
PANORAMA
The general pipeline for this homework includes the following steps:
1. Given N input images, set one image as a reference
2. Detect feature points from images and correspondences between pairs of images
3. Estimate the homographies between images using RANSAC
4. Warp the images to the reference image
5. Composite them
REQUIREMENTS
⚫ You need to implement your own code for RANSAC. Do not use RANSAC functions provided by libraries.
⚫ The final panorama image should have no seams between stitched images. Use image blending methods
such as alpha blending, multi-band blending, or Poisson image blending to avoid seams. Your homework
will be scored based on the quality of your results.
Your report must include:
⚫ Detailed discussion on your implementation
⚫ Your results with a detailed discussion
⚫ Limitations of the techniques that you found
You must upload a single zip file that contains the following to the LMS:
⚫ code/ – a directory containing all your code for this assignment
⚫ images/ – a directory containing your input images and their results
⚫ report.pdf – your report as a PDF file
Due: Nov. 28
th, 23:59
Penalty for late submission
⚫ 1 day: 70%
⚫ 2 days: 30%
⚫ 3 days: 0%
RUBRIC
⚫ 40 pts: Image alignment
⚫ 20 pts: Image blending
⚫ 40 pts: Report
Your homework will be scored based on your report, and I am not going to compile or run your code. Thus, your
report must include all necessary details of your implementation and results.
