AI Paper Atlas

Research map / 3D vision / Depth and stereo

Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision

Jinnyeong Kim, Juhyung Choi, Woohyeok Kim, Sunghyun Cho, Seung-Hwan Baek

ECCV 2026 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 0 citations (OpenAlex)

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
use monocular depth instead of optical flow for alignment (ablation)DMEB · Real modest DR, single-shot multi-cameraPSNR-mu: 35.84 -> 37.09Improved
use single-view LiDAR-anchored depth instead of monocular depth (ablation)DMEB · Real modest DR, single-shot multi-cameraPSNR-mu: 37.09 -> 37.90Improved
use multi-view LiDAR-guided fusion instead of single-view LiDAR depth (ablation)DMEB · Real modest DR, single-shot multi-cameraPSNR-mu: 37.90 -> 39.40Improved
remove depth and align with optical flow (ablation)DMEB · Real modest DRPSNR-mu: 39.40 -> 35.84Hurt
switch from multi-shot single-camera to single-shot multi-camera inputHDR Transformer · Real modest DRPSNR-mu: 31.26 -> 33.61Improved
switch from multi-shot single-camera to single-shot multi-camera inputAFUNet · Real modest DRPSNR-mu: 29.64 -> 32.25Improved
switch from multi-shot single-camera to single-shot multi-camera inputDMEB · Real modest DRPSNR-mu: 30.72 -> 39.40Improved
increase camera count from three to eight (ablation)DMEB · Real and syntheticdynamic rangeImproved
use DMEB instead of HDR Transformer on ultra DR scenesDMEB · Real ultra DR, single-shot multi-cameraHDR-VDP: PSNR-mu 38.74 -> 39.17, HDR-VDP 9.40 -> 9.16Mixed
use DMEB instead of AFUNet on synthetic benchmarkDMEB · Synthetic benchmark (CARLA)PSNR-mu: 33.52 -> 34.72Improved
use DMEB on zero-shot external two-view dataDMEB · Choi 2-viewPSNR-mu: 26.33 and 25.39 -> 33.00Improved
use DMEB output for YOLOv8 detectionDMEB · YOLOv8 detection, 90 annotated framesRecall/F1: 0.78/0.63 and 0.81/0.67 -> 0.83/0.73Improved

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