OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911366356402176 |
|---|---|
| author | Lee, Hyunseo Kim, Sang Min Shin, Ho Kyung Kim, Taeheon Nam, Woo-Jeoung |
| author_facet | Lee, Hyunseo Kim, Sang Min Shin, Ho Kyung Kim, Taeheon Nam, Woo-Jeoung |
| contents | Synthetic Aperture Radar (SAR) provides robust all-weather imaging capabilities; however, translating SAR observations into photo-realistic optical images remains a fundamentally ill-posed problem. Current approaches are often hindered by the inherent speckle noise and geometric distortions of SAR data, which frequently result in semantic misinterpretation, ambiguous texture synthesis, and structural hallucinations. To address these limitations, a novel SAR-to-Optical (S2O) translation framework is proposed, integrating three core technical contributions: (i) Cross-Modal Semantic Alignment, which establishes an Optical-Aware SAR Encoder by distilling robust semantic priors from an Optical Teacher into a SAR Student (ii) Semantically-Grounded Generative Guidance, realized by a Semantically-Grounded ControlNet that integrates class-aware text prompts for global context with hierarchical visual prompts for local spatial guidance; and (iii) an Uncertainty-Aware Objective, which explicitly models aleatoric uncertainty to dynamically modulate the reconstruction focus, effectively mitigating artifacts caused by speckle-induced ambiguity. Extensive experiments demonstrate that the proposed method achieves superior perceptual quality and semantic consistency compared to state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06835 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation Lee, Hyunseo Kim, Sang Min Shin, Ho Kyung Kim, Taeheon Nam, Woo-Jeoung Computer Vision and Pattern Recognition Artificial Intelligence Synthetic Aperture Radar (SAR) provides robust all-weather imaging capabilities; however, translating SAR observations into photo-realistic optical images remains a fundamentally ill-posed problem. Current approaches are often hindered by the inherent speckle noise and geometric distortions of SAR data, which frequently result in semantic misinterpretation, ambiguous texture synthesis, and structural hallucinations. To address these limitations, a novel SAR-to-Optical (S2O) translation framework is proposed, integrating three core technical contributions: (i) Cross-Modal Semantic Alignment, which establishes an Optical-Aware SAR Encoder by distilling robust semantic priors from an Optical Teacher into a SAR Student (ii) Semantically-Grounded Generative Guidance, realized by a Semantically-Grounded ControlNet that integrates class-aware text prompts for global context with hierarchical visual prompts for local spatial guidance; and (iii) an Uncertainty-Aware Objective, which explicitly models aleatoric uncertainty to dynamically modulate the reconstruction focus, effectively mitigating artifacts caused by speckle-induced ambiguity. Extensive experiments demonstrate that the proposed method achieves superior perceptual quality and semantic consistency compared to state-of-the-art approaches. |
| title | OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.06835 |