Simulating human visual imagination: Scaling and placement of objects in procedural generation of 3D scenes
Bibliographic record
Abstract
Although there is already quite a bit of research on the uses of imagination, there is a gap involving how exactly mental images are created (Davies et al., 2011), and more specifically, how humans use their imagination to create scenes.This thesis describes the placement and scaling of objects in the creation of scenes in the visual imagination.To examine this topic, I created 30 images in Unity using scene descriptions generated by SOILIE 3D and 30 images that applied additional constraints based on an improved model of placement and scaling of objects.Contrasting these pairs illustrates the key aspects of human scene creation and demonstrates that my model is more realistic.While the previous model was too theoretical and failed to take many aspects of human cognition into account, applying research in neuroscience and human scene understanding has allowed for an improved model that is more consistent with a human perspective of scenes.This work would not have been possible without the guidance and support of such a wonderful group of people that I have the good fortune of being surrounded by.First and foremost, I would like to thank my supervisor, Dr. Jim Davies.From being the voice of reason during my panicked ramblings, to answering even the most basic of questions with utmost consideration, your tireless support has guided me through these tumultuous times.I have been benefiting from your advice since our first meeting, when you encouraged me to pursue a master's degree and work with you.Were it not for you, I would still be trudging through a second degree with the hopes of one day being where I am now.These past years I have had the opportunity to work alongside and learn from members of the academic community within Carleton University.I would like to thank Dr. Ida Toivonen for taking the time to be on my committee and for always asking the hard questions.While I undoubtedly still make mistakes when choosing my words, I am guided by your voice, questioning whether I am truly saying what I mean to say.Thanks to Dr. Robert West, for also agreeing to be on my committee and for your helpful suggestions on clarifying my manuscript.Thank you Dr. Craig Leth
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".