AI Paper Atlas

Research map / Detection and segmentation / CNN features

End-to-End High Dynamic Range Camera Pipeline Optimization

Nicolas Robidoux, Luis E. Garcia Capel, Dong-eun Seo, Avinash Sharma, Federico Ariza, Felix Heide

CVPR 2021 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 28 citations (OpenAlex)

Check 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
Jointly optimize sensor, ISP, and detector weights instead of using expert-tuned settingsHDR camera pipeline with YOLOv4 · Automotive object detection test setmAP (IoU>0.5): 0.250 -> 0.584Improved
Jointly optimize sensor, ISP, and detector weights instead of using Mosleh et al. optimizationHDR camera pipeline with YOLOv4 · Automotive object detection test setmAP (IoU>0.5): 0.367 -> 0.584Improved
Jointly optimize sensor, ISP, and detector weights instead of using expert-tuned settingsHDR camera pipeline with YOLOv4 · Automotive object detection test setmAP (IoU>0.75): 0.244 -> 0.561Improved
Jointly optimize sensor, ISP, and detector weights instead of using Mosleh et al. optimizationHDR camera pipeline with YOLOv4 · Automotive object detection test setmAP (IoU>0.75): 0.356 -> 0.561Improved
Jointly optimize sensor, ISP, and detector weights instead of using expert-tuned settingsHDR camera pipeline with YOLOv4 · Automotive object detection test setmAR: 0.235 -> 0.560Improved
Jointly optimize sensor, ISP, and detector weights instead of using Mosleh et al. optimizationHDR camera pipeline with YOLOv4 · Automotive object detection test setmAR: 0.352 -> 0.560Improved
Use the proposed perceptual optimization rather than the combined Mosleh et al. and expert-tuned settingsAR0231AT + AP0202AT HDR pipeline · HDR perceptual optimization labFSITM mean: 0.335 -> 0.333Improved
Use the proposed perceptual optimization rather than the combined Mosleh et al. and expert-tuned settingsAR0231AT + AP0202AT HDR pipeline · HDR perceptual optimization labCWLP mean: 4.083 -> 4.045Improved
Use the proposed perceptual optimization rather than the combined Mosleh et al. and expert-tuned settingsAR0231AT + AP0202AT HDR pipeline · HDR perceptual optimization labZippering mean = worst: 0.068 -> 0.071Hurt
Use the proposed perceptual optimization rather than the combined Mosleh et al. and expert-tuned settingsAR0231AT + AP0202AT HDR pipeline · HDR perceptual optimization labSNR worst: 23.60 -> 24.89Improved
Continue joint optimization from one iteration to convergence (ablation)Proposed HDR camera pipeline with YOLOv4 · Automotive object detection test setmAP (IoU>0.5): 0.563 -> 0.584Improved
Continue joint optimization from one iteration to convergence (ablation)Proposed HDR camera pipeline with YOLOv4 · Automotive object detection test setmAP (IoU>0.75): 0.540 -> 0.561Improved

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