A perceptually validated model for surface depth hallucination
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Capturing detailed surface geometry currently requires specialized equipment such as laser range scanners, which despite their high accuracy, leave gaps in the surfaces that must be reconciled with photographic capture for relighting applications. Using only a standard digital camera and a single view, we present a method for recovering models of predominantly diffuse textured surfaces that can be plausibly relit and viewed from any angle under any illumination. Our multiscale shape-from-shading technique uses diffuse-lit/flash-lit image pairs to produce an albedo map and textured height field. Using two lighting conditions enables us to subtract one from the other to estimate albedo. In the absence of a flash-lit image of a surface for which we already have a similar exemplar pair, we approximate both albedo and diffuse shading images using histogram matching. Our depth estimation is based on local visibility. Unlike other depth-from-shading approaches, all operations are performed on the diffuse shading image in image space, and we impose no constant albedo restrictions. An experimental validation shows our method works for a broad range of textured surfaces, and viewers are frequently unable to identify our results as synthetic in a randomized presentation. Furthermore, in side-by-side comparisons, subjects found a rendering of our depth map equally plausible to one generated from a laser range scan. We see this method as a significant advance in acquiring surface detail for texturing using a standard digital camera, with applications in architecture, archaeological reconstruction, games and special effects.
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.
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 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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 it