Designing for Depth Estimation

An ongoing research thread in the Lab for Cognition and Attention in Time and Space (Lab for CATS) is evaluating the behaviour of monocular depth models (depth prediction methods that rely only on a single image). This is a mathematically ill-posed problem, and performing monocular depth estimation relies on a set of heuristics collectively known as monocular depth cues. Like most neural network-based methods, monocular depth models operate largely as black box systems, making it unclear which cues are driving their predictions and how robust they might be to circumstantial changes to cue reliability.

In this project, our lab is attempting to develop new ways of evaluating the behaviour of monocular depth models in order to better understand what depth cues are most important to their predictions and how well these models respond to dynamic changes in cue reliability. In order to explore this, we will be designing and editing scenes in Blender in order to isolate and control specific depth cues, and then analyze the change in model behaviour. I expect that the majority of time this academic year will be devoted to developing and editing Blender scenes, and this will be the primary task of students when initially joining the project.

In your application, please indicate if you are looking to join this semester (Fall 2026) or next semester (Spring 2027).

Name of research group, project, or lab
Lab for CATS
Why join this research group or lab?

The Lab for CATS is a collaborative and supportive environment to learn about vision and perception modeling. Students who join the lab get a chance to learn about many of the general aspects of research, while also digging into a specific aspect of vision research.

For this project specifically, students will gain experience with a popular open-source 3D graphics engine (Blender), as well an introduction to a number of conceptual concepts important to spatial vision and depth prediction. 

Logistics Information:
Project categories
Computer Science
Cognitive Science
Computer Vision
Student ranks applicable
First-year
Sophomore
Junior
Senior
Student qualifications

The most important qualification is an interest in the problem and a willingness to deal with the sometimes rather tedious process of scene editing in Blender. Prior experience in creating 3D graphics or CAD modeling could be beneficial (particularly if it is with Blender specifically!), but is not required. There are no physical requirements for this position.

When applying for this position, please address the following prompts (please keep your answers brief; no more than 400 words per question):

  1. What specifically interests you in this project? What are you hoping to bring to the project, and what do you hope to get out of it?
  2. Describe a time that you set out to solve a problem that was challenging for you and that did not have a clear solution ahead of time. Examples of things you might discuss include: What strategies did you try? What did you learn (either about the problem or about yourself and how you learn)? How did you deal with getting stuck? 

Please be sure to answer these questions with your own words (no AI-generated responses).

Time commitment
Fall - Part Time
Spring - Part Time
Compensation
Academic Credit
Number of openings
3
Techniques learned

Students will gain experience with Blender. More general concepts include exposure to computer graphics and scene rendering, and the principles of monocular depth estimation. Students will also get experience working with remote computing resources.

Project start
Fall or Spring Semester
Contact Information:
Mentor
cwloka@hmc.edu
Principal Investigator
Name of project director or principal investigator
Calden Wloka
Email address of project director or principal investigator
cwloka@hmc.edu
3 sp. | 0 appl.
Time commitment
Fall - Part Time (+1)
Fall - Part TimeSpring - Part Time
Project categories
Cognitive Science (+2)
Computer ScienceCognitive ScienceComputer Vision