Research map / Detection and segmentation / CNN features
SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements
Haiyang Xie, Xi Shen, Shihua Huang, Qirui Wang, Zheng Wang
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 |
|---|---|---|---|
| use green-channel guidance instead of no guidance in GGLE (ablation) | SimROD (YoloX-Tiny) · LOD | AP50: 45.1 -> 46.3 | Improved |
| use red guidance in GGLE (ablation) | SimROD · LOD | AP50: 45.1 -> 44.9 | Hurt |
| use blue guidance in GGLE (ablation) | SimROD · LOD | AP50: 45.1 -> 44.2 | Hurt |
| guide with all RGGB channels instead of GG only (ablation) | SimROD · LOD | AP50: 46.3 -> 46.2 | Hurt |
| guide with GG only vs RGGB on Pascal-Raw (ablation) | SimROD · Pascal-Raw | AP50: 94.5 -> 95.1 | Improved |
| halve green channel sampling (0.5x) for DIAP (ablation) | DIAP · LOD | AP50: 42.0 -> 40.3 | Hurt |
| halve green channel sampling on Pascal-Raw (ablation) | DIAP · Pascal-Raw | AP50: 94.2 -> 94.3 | No clear effect |
| replace DIAP image-level module by GGE (4 params) (ablation) | YoloX-Tiny · ROD | AP: 30.7 -> 30.9 | No clear effect |
| replace DIAP module by GGE on Pascal-Raw (ablation) | YoloX-Tiny · Pascal-Raw | AP: 68.7 -> 68.4 | No clear effect |
| replace DIAP module by GGE on LOD (ablation) | YoloX-Tiny · LOD | AP50: 43.4 -> 46.2 | Improved |
| SimROD vs DIAP on ROD with YoloX-Tiny | SimROD · ROD | AP: 30.7 -> 33.1 | Improved |
| SimROD vs RAW-Adapter on over-exposed ADE20K-Raw | SimROD · ADE20K-Raw (over-exposure) | mIoU: 46.62 -> 45.96 | Hurt |
Closest papers by meaning
- Towards RAW Object Detection in Diverse Conditions (CVPR 2025 · similarity 0.86)
- RAWild: Toward Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling (NeurIPS 2026 · similarity 0.85)
- ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge (CVPR 2025 · similarity 0.84)
- Guiding a Harsh-Environments Robust Detector via RAW Data Characteristic Mining (AAAI 2024 · similarity 0.84)
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · similarity 0.82)
- TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection (AAAI 2025 · similarity 0.82)
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.
