AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

RAW-Adapter: Adapting Pretrained Visual Model to Camera RAW Images

Ziteng Cui, Tatsuya Harada

ECCV 2024 · Vision-language and multimodal › Human and embodied modeling · approach: Scientific domain vision datasets

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 changedWhereMeasuredEffect
add kernel predictor P_K (gain ratio and adaptive Gaussian denoise) (ablation)RAW-Adapter on RetinaNet ResNet-50 · PASCAL RAW (dark)mAP: 82.6 -> 85.0Improved
add kernel predictor P_K (ablation)RAW-Adapter on RetinaNet ResNet-50 · PASCAL RAW (normal)mAP: 89.2 -> 89.2No clear effect
add matrix predictor P_M (white balance and CCM) (ablation)RAW-Adapter · PASCAL RAW (dark)mAP: 85.0 -> 86.2Improved
add implicit 3D LUT (ablation)RAW-Adapter · PASCAL RAW (over-exp and dark)mAP: dark 86.2 -> 86.3; normal 89.5 -> 89.4No clear effect
add model-level adapters M (ablation)RAW-Adapter · PASCAL RAW (normal/over-exp/dark)mAP: dark 86.3 -> 86.6; normal 89.4 -> 89.7; over-exp 89.0 -> 89.5Improved
add model-level adapters M (ablation)RAW-Adapter on LOD · LOD, RetinaNetmAP: 61.6 -> 62.1Improved
increase NILUT MLP dim from 32 to 64 or 128 (ablation)RAW-Adapter · ADE20K RAWmIoU: 47.95 -> 48.02 (dim 64)No clear effect
reduce NILUT MLP dim from 32 to 16 (ablation)RAW-Adapter · ADE20K RAW (normal)mIoU: 47.95 -> 47.37Hurt
apply human-vision ISP methods (InvISP, LiteISP) to RAW before segmentation in darkSegformer MIT-B5 · ADE20K RAW (dark)mIoU: 37.55 (demosaicing) -> 4.03 (InvISP)Hurt
use RAW-Adapter instead of Dirty-PixelRetinaNet ResNet-50 · PASCAL RAW (dark)mAP: 83.6 -> 86.6Improved
use RAW-Adapter on small backbone MIT-B0Segformer · ADE20K RAW (dark)mIoU: 24.89 -> 25.06 (vs Dirty-Pixel)Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy