An Optimal Transport Analogue of the Rudin–Osher–Fatemi Model and Its Corresponding Multiscale Theory
Bibliographic record
Abstract
Abstract. In the first part of this paper we develop a theory for image restoration with a learned regularizer that is analogous to that of Meyer’s geometric characterization of solutions of the classical variational method of Rudin–Osher–Fatemi (ROF). The learned regularizer we use is a Kantorovich potential for an optimal transport problem of mapping a distribution of noisy images onto clean ones, as first proposed by Lunz, Öktem, and Schönlieb. We show that the effect of their restoration method on the distribution of the images is an explicit Euler discretization of a gradient flow on probability space, while our variational problem, dubbed Wasserstein ROF (WROF), is the corresponding implicit Euler discretization. We obtain our geometric characterization of the solution in this learned regularizer setting by first proving a much more general convex analysis theorem for variational problems having solutions characterized by projections. We then use optimal transport arguments to obtain the corresponding theorem for WROF from this general result, as well as a natural decomposition of a transport map into large scale “features” and small scale “details,” where scale refers to the magnitude of the transport distance. In the second part of the paper we leverage our theory for restoration with learned regularizers to analyze two algorithms which iterate WROF. We refer to these as iterative regularization and multiscale transport. For the former we obtain a proof of convergence to the clean data. For the latter we produce successive approximations to the target distribution that match it up to finer and finer scales. These two algorithms are in complete analogy to well-known effective methods based on ROF for iterative denoising, respectively hierarchical image decomposition. We also obtain an analogue of the Tadmor–Nezzar–Vese energy identity, which decomposes the Wasserstein 2 distance between two measures into a sum of nonnegative terms that correspond to transport costs at different scales.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".