@online{Fatima2602.03760,
TITLE = {{{RAW}Det}-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized {RAW} Images},
AUTHOR = {Fatima, Mishal and Agnihotri, Shashank and Gandikota, Kanchana Vaishnavi and Moeller, Michael and Keuper, Margret},
LANGUAGE = {eng},
URL = {https://arxiv.org/abs/2602.03760},
EPRINT = {2602.03760},
EPRINTTYPE = {arXiv},
YEAR = {2026},
ABSTRACT = {Most vision models are trained on RGB images processed through ISP pipelines optimized for human perception, which can discard sensor-level information useful for machine reasoning. RAW images preserve unprocessed scene data, enabling models to leverage richer cues for both object detection and object description, capturing fine-grained details, spatial relationships, and contextual information often lost in processed images. To support research in this domain, we introduce RAWDet-7, a large-scale dataset of ~25k training and 7.6k test RAW images collected across diverse cameras, lighting conditions, and environments, densely annotated for seven object categories following MS-COCO and LVIS conventions. In addition, we provide object-level descriptions derived from the corresponding high-resolution sRGB images, facilitating the study of object-level information preservation under RAW image processing and low-bit quantization. The dataset allows evaluation under simulated 4-bit, 6-bit, and 8-bit quantization, reflecting realistic sensor constraints, and provides a benchmark for studying detection performance, description quality & detail, and generalization in low-bit RAW image processing. Dataset & code upon acceptance.},
}