Research map / Detection and segmentation / CNN features
Beyond RGB: Adaptive Parallel Processing for RAW Object Detection
Shani Gamrian, Hila Barel, Feiran Li, Masakazu Yoshimura, Daisuke Iso
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| apply ISP functions in parallel with shared encoder instead of sequentially (ablation) | RAM · LOD-Dark | mAP: 29.9 -> 35.2 | Improved |
| apply ISP functions in parallel instead of sequentially (ablation) | RAM · LOD-Normal | mAP: 35.1 -> 40.1 | Improved |
| replace sRGB ISP with RAM on RAW input | Faster R-CNN ResNet18 · ROD-Night | mAP: 38.9 -> 44.5 | Improved |
| scale backbone from ResNet18 to ResNet50 on RAW (ablation) | Faster R-CNN on RAW · ROD-Night | mAP: 30.4 -> 34.7 | Improved |
| use tiny RAM-T with fewer than half the parameters (ablation) | RAM · ROD-Night | mAP: 44.5 -> 44.2 | No clear effect |
| apply RAM to sRGB images instead of RAW (ablation) | RAM · LOD-Dark | mAP: 34.9 -> 32.9 | Hurt |
| use RAM on noisy RAW instead of sRGB | DINO ResNet50 · ROD-Night strong noise | mAP: 38.9 -> 42.4 | Improved |
| use RAM under snow weather instead of sRGB | DINO ResNet50 · ROD-Night snow | mAP: 37.4 -> 53.2 | Improved |
| train RAM only with frozen COCO-pretrained YOLOX-X detector | RAM · NOD-Sony | mAP: 24.4 -> 29.6 | Improved |
| train one model on all four RAW datasets instead of each separately (ablation) | RAM · NOD-Sony | mAP: 32.8 -> 35.8 | Improved |
| add brightness adjustment function (ablation) | RAM · LOD-Normal | Shapley value | No clear effect |
| use reverse-hourglass Feature Fusion instead of single-layer convolution (ablation) | RAM · multiple RAW datasets | Shapley value | Improved |
Closest papers by meaning
- Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection (ICCV 2025 · similarity 0.90)
- Towards RAW Object Detection in Diverse Conditions (CVPR 2025 · similarity 0.88)
- Guiding a Harsh-Environments Robust Detector via RAW Data Characteristic Mining (AAAI 2024 · similarity 0.87)
- ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge (CVPR 2025 · similarity 0.87)
- AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection (NeurIPS 2024 · similarity 0.86)
- RAWild: Toward Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
