Front2Back: Single View 3D Shape Reconstruction via Front to Back\n Prediction
Bibliographic record
Abstract
Reconstruction of a 3D shape from a single 2D image is a classical computer\nvision problem, whose difficulty stems from the inherent ambiguity of\nrecovering occluded or only partially observed surfaces. Recent methods address\nthis challenge through the use of largely unstructured neural networks that\neffectively distill conditional mapping and priors over 3D shape. In this work,\nwe induce structure and geometric constraints by leveraging three core\nobservations: (1) the surface of most everyday objects is often almost entirely\nexposed from pairs of typical opposite views; (2) everyday objects often\nexhibit global reflective symmetries which can be accurately predicted from\nsingle views; (3) opposite orthographic views of a 3D shape share consistent\nsilhouettes. Following these observations, we first predict orthographic 2.5D\nvisible surface maps (depth, normal and silhouette) from perspective 2D images,\nand detect global reflective symmetries in this data; second, we predict the\nback facing depth and normal maps using as input the front maps and, when\navailable, the symmetric reflections of these maps; and finally, we reconstruct\na 3D mesh from the union of these maps using a surface reconstruction method\nbest suited for this data. Our experiments demonstrate that our framework\noutperforms state-of-the art approaches for 3D shape reconstructions from 2D\nand 2.5D data in terms of input fidelity and details preservation.\nSpecifically, we achieve 12% better performance on average in ShapeNet\nbenchmark dataset, and up to 19% for certain classes of objects (e.g., chairs\nand vessels).\n
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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.002 |
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".