AI Paper Atlas

Research map / 3D vision / Depth and stereo

Reconstructing Dense Depth of Dark Scenes with Sparse LiDAR, Noisy Events, and Blurry RGB

Jianbo Cao, Yuqi Han, Siming Zheng, Bo Wang, Tong Guo, Jinli Suo

ECCV 2026 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 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
add event-guided feature restoration (EFR) instead of a deblurrer (ablation)ERU-Net · Night-RIDE (real-world)RMSE: 4.215 -> 1.505Improved
add hybrid-guidance confidence module (HGCM) event guidance (ablation)ERU-Net · Night-RIDE (real-world)RMSE: 2.345 -> 1.505Improved
add EFR instead of deblurrer (ablation)ERU-Net · Night-RIDE (real-world)MAE: 1.682 -> 0.502Improved
add HGCM (ablation)ERU-Net · Night-RIDE (real-world)MAE: 0.892 -> 0.502Improved
add HGCM (ablation)ERU-Net · Night-RIDE (real-world)delta1: 98.1 -> 99.6Improved
add EFR instead of deblurrer (ablation)ERU-Net · Night-RIDE (real-world)delta1: 92.5 -> 99.6Improved
replace EVSSM+Mari-DC two-stage pipeline with end-to-end ERU-NetERU-Net · KITTI (simulated blur)RMSE: 1093.50 -> 888.20Improved
replace EVSSM+Mari-DC with ERU-NetERU-Net · NYUv2 (500 sparse points)RMSE: 3.902 -> 2.603Improved
use REFID instead of EFNet as event deblurring pre-processingMari-DC · Event-deblurring + depth completion (Table 2)RMSE: 3.352 -> 3.145Improved
use REFID instead of EFNet pre-processingCSPN · Event-deblurring + depth completion (Table 2)RMSE: 6.090 -> 5.782Improved
replace restore-then-complete event pipeline (REFID+Mari-DC) with ERU-NetERU-Net · Event-deblurring + depth completion (Table 2)RMSE: 3.145 -> 2.603Improved
add three-stage training with joint fine-tuningERU-Net · KITTI / NYUv2RMSEImproved

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