Computer Graphics (CG) enables artists to realize their creative visions.
Technically, one is concerned with efficiently simulating light transport for photorealistic rendering,
finding the right parametrization for the shape and appearance of objects, and making these digital models accessible to the artist.
Creating digital content is a tedious process, which is alleviated by Computer Vision (CV) by reconstructing real scenes from natural images.
This course will explore the recent trend of using Deep Learning (DL) for the above-mentioned tasks; neural rendering, generative networks, disentangled representation learning, and reconstruction using neural networks. The part of the course will introduce the essential tools (geometric models, probabilistic models, optimization, sampling), those needed to understand the advanced topics covered in the main part (self-supervised and generative models, such as VAEs and GANs).
A central theme is the learning of neural representations from labeled and unlabeled data.
At one end, we will discuss approaches that can reconstruct a person photorealistic, from a single image and up to the scale of wrinkles, by using a volumetric grid with thousands of parameters.
On the other end, we will study techniques for learning compact and meaningful embeddings, such as a parametric face model that decomposes expression, appearance, and pose
and makes these latent dimensions controllable by the artist.
At the end of the course, students will be able to work with and deeply understand a diverse spectrum of DL tools and be prepared to conduct research on how to create new models that yield both, high visual quality and have artistic utility.
The course is interactive, with three assignments (solved in a randomly assigned group of two), paper reading and presentations (individual), and course projects (teams of 2-3 students).
On top of the classes, office hours will be offered by the TA and me (instructor) once a week; time TBD in the first week, based on your constraints. Moreover, both of us will be available for immediate discussion and questions on the Piazza discussion platform.
Registration and official listing:
CPSC 533R
Instructor: Helge Rhodin (rhodin@cs.ubc.ca
)
Office hours (drop-in): TBD
Teaching Assistant: Xingzhe He
Office hours (drop-in): TBD
Classes: Tuesday and Thursday 9:30 11:00 PDT (winter term 2)
Room: DMP 101 (and zoom?)
Piazza: Discussions will be on Piazza
Compute: The assignments and course projects will deal with images and require CUDA-capable GPUs for training.
You can either use your own GPU, open cloud services like google colab, or UBC machines lin01.students.cs.ubc.ca to lin25.students.cs.ubc.ca.
Math. This year's iteration will dive deeper into probabilistic models, which requires a basic understanding of probability theory (mean, std, expectation, Gaussian distribution) and basic math (integration, solving equations, working with inequalities, bounds, limits).
Machine Learning. It is required to first study CPSC 340 or an equivalent course. Before starting this course, the following ML terms should be familiar to you: stochastic gradient descent and momentum; classification and regression; weight initialization and data whitening; training, validation and test set; convolution and translational invariance; and regularization and weight decay.
Please contact me if you have any doubts.
Python. The exercises are designed to prepare students for the practical project and provide a step-by-step introduction to the PyTorch machine learning framework. While no prior knowledge on PyTorch is required, essential python experience is expected; no python programming tutorial will be offered.
Prior courses in CG and CV are a plus and course projects that build upon these are encouraged.
Audits are permitted on a case-by-case basis; please contact me prior to the start and join for the first lecture. Auditing students have to participate actively in the reading part of the class, i.e., reading of the papers, writing a review, and participating in the discussion. Audits are more than welcome to also work on the assignments or course project, but this is not a requirement.
The course contains three assignments that add points to the final grade, however, their primary goal is to prepare you for the project.
The first assignment is to set up a general training framework that lets one experiment with different datasets, neural network architectures, and objective functions. This framework will be extended and used in the remaining two assignments and also the final course project.
Instead of step-by-step instructions, exercises are posed as high-level tasks. Questions are set up to train independent thinking, which is integral to solving actual problems in research and industry settings. This does not mean that you are without support; you are highly encouraged to search online and consult the abundance of deep learning tutorials as a basis for your solution. Furthermore, office hours are set up to provide personal assistance.
Academic Integrity. Assignments must be solved in teams of two, using the available course material and other online sources. You are neither allowed to copy nor look at parts of any of the assignments from anyone else except your teammate.
Accordingly, it is not allowed to post solutions online or distribute them in (private) forums.
The university policies on academic integrity are rigorously applied.
Teamwork and submission. One solution must be submitted per group via Canvas, but we expect that the solution was derived together (via video chat sessions) and both members must be able to explain all parts. Groups are assigned for each assignment at random by the instructor to facilitate diverse interactions and equal opportunities.
Deadline and grading.
Assignments will be due on the dates specified in the schedule, always at 11:59 pm PST.
A late submission by one day will still be accepted but reduces the score by -25%.
The grading is based on correctness and completeness, as detailed in each exercise description.
The second half of the course will constitute a reading group, focussing on seminal and latest research. Each student will write reviews every week and is expected to participate actively in the discussion, along with presenting once during the course. Preferences will be considered for the presentation topic assignment.
Reviews. All students are expected to read one of the two papers that will be presented and discussed in each class. Nevertheless, it is recommended to at least skim through both the papers. Each presentation will be followed by an in-depth discussion on technical aspects, relations to other works, and practical utility. To initiate and start new arguments, a short review of the selected paper will have to be submitted on the day before the class. Try to raise non-obvious aspects with the following:
Keep your review concise (less than half a page) and self-contained.
Moderation.
Each presentation is followed by a ~15-minute discussion. You will moderate the discussion of the paper presented by somebody else in the lecture following yours. It is your task to start the discussion by asking suitable questions and leading the subsequent discussion. We will provide you with reviews of the other students, which you can use as a starting point. Note, the moderation replaces the peer-review done in previous iterations of this course.
Presentation. Every student presents one research paper. The presentation should be compact and precisely 15 minutes long. Focus on the most crucial points, those needed to understand the content, novelty, and impact of the given work. Most importantly, draw links to previous presentations, lecture content, and the related work you know. Such an embedding into a broader context will make your presentation unique and stimulating, especially for those who have read the underlying paper in detail.
You can take the paper illustrations and other available online material, such as videos supplementing the paper, as a basis for your presentation, as long as you reference the source adequately on each slide.
You will be the expert and be required to study the paper in sufficient depth to answer questions and trigger a rich discussion.
Practice your talk before, ideally in front of some friends, to get the timing and the messages right. Note that a part of your audience will have read the paper in detail and others will only have skimmed through. Therefore, try to address experts and newcomers alike. The tutor will assist you in this and give feedback on your planned presentation, make an appointment with him in advance.
The whole course is structured to prepare for the final research project. The goal is to either extend an existing approach, combine existing tools for solving a new problem, or to come up with an entirely new algorithm. Some topics and open research problems are given in class, but we highly encourage you to come up with your own idea on the basis of your unique background and experience. Projects can deviate from the core lecture topics, as longs as they are within CG, CV, and ML. You are encouraged to work in groups of two to three students. Joining forces will allow you to complement your strengths and work on more challenging and rewarding problems. Nevertheless, all team members must have unique responsibilities, which have to be explicitly listed, and be involved in all of the following project stages:
Deadlines and grading. Project proposal, pitch, report, and final presentations will be due on the dates and times specified in the schedule linked above (pitch ~mid-term, project presentations in the last two weeks, partial report submissions during the term, final report submission on the 14th of Dec.). A late submission reduces the gained points by -25% per day. The grade will mainly depend on the project definition, how well you present them in the report, how distinctly you position your work in the related literature, how thorough your experiments are, and how thoughtfully your contribution is derived. We value quality over quanity, focus on one aspect and keep things as simple as possible.