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 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.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".