RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling
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_ | 1866913098484416512 |
|---|---|
| author | Liu, Shuhong Chang, Gengjia Liu, Jun Chu, Xuangeng Zheng, Yinqiang Harada, Tatsuya Cui, Ziteng |
| author_facet | Liu, Shuhong Chang, Gengjia Liu, Jun Chu, Xuangeng Zheng, Yinqiang Harada, Tatsuya Cui, Ziteng |
| contents | Camera sensor RAW data offers intrinsic advantages for object detection, including deeper bit depth, preserved physical information, and freedom from image signal processor (ISP) distortions. However, varying exposure conditions, spectral sensitivities, and bit depths across devices introduce substantially larger domain gaps than sRGB, making sensor-agnostic generalization a fundamental challenge. In this study, we present \textbf{RAWild}, a physics-guided global-local tone mapping framework for sensor-agnostic RAW object detection. By factoring sensor-induced variations into a global tonal correction and a spatially adaptive local color adjustment, both driven by RAW distribution priors, our framework enables a single network to train jointly across heterogeneous sensors. To further support cross-sensor generalization, we construct a physics-based RAW simulation pipeline that synthesizes realistic sensor outputs spanning diverse spectral sensitivities, illuminants, and sensor non-idealities. Extensive experiments across multiple RAW benchmarks covering bit depths from 10 to 24 demonstrate state-of-the-art (SOTA) performance under single-dataset, mixed-dataset, and challenging robustness settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05941 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling Liu, Shuhong Chang, Gengjia Liu, Jun Chu, Xuangeng Zheng, Yinqiang Harada, Tatsuya Cui, Ziteng Computer Vision and Pattern Recognition Camera sensor RAW data offers intrinsic advantages for object detection, including deeper bit depth, preserved physical information, and freedom from image signal processor (ISP) distortions. However, varying exposure conditions, spectral sensitivities, and bit depths across devices introduce substantially larger domain gaps than sRGB, making sensor-agnostic generalization a fundamental challenge. In this study, we present \textbf{RAWild}, a physics-guided global-local tone mapping framework for sensor-agnostic RAW object detection. By factoring sensor-induced variations into a global tonal correction and a spatially adaptive local color adjustment, both driven by RAW distribution priors, our framework enables a single network to train jointly across heterogeneous sensors. To further support cross-sensor generalization, we construct a physics-based RAW simulation pipeline that synthesizes realistic sensor outputs spanning diverse spectral sensitivities, illuminants, and sensor non-idealities. Extensive experiments across multiple RAW benchmarks covering bit depths from 10 to 24 demonstrate state-of-the-art (SOTA) performance under single-dataset, mixed-dataset, and challenging robustness settings. |
| title | RAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.05941 |