Multi-Temporal Latent Diffusion Transformers for Cloud Removal in Remote Sensing Images
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
Cloud removal is an imperative pre-processing task for applications which extract land surface information from remote sensing images. While previous SOTA approaches to cloud removal have leveraged diffusion models, these methods operate in pixel space, and the feasibility of latent-space reconstruction techniques has been unexplored in this domain. In this work, we introduce multi-temporal latent diffusion transformers (MT-DiT), a novel framework that uses transformer-based diffusion in latent space to reconstruct cloud-covered regions. By compressing cloudy images into latent patch embeddings and integrating historical multi-temporal observations through a cross-attention conditioning mechanism, MT-DiT is able to capture rich spatiotemporal context from latent space representations. This design extends classifier-free guidance for diffusion transformers (DiT) to multi-temporal latent conditioning, enabling more detailed and consistent restoration of obscured land surfaces. Experiments on a publicly available dataset show that MT-DiT outperforms existing methods in key metrics, underscoring the advantages of latent diffusion model and transformer architectures for land surface reconstruction.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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