AI Paper Atlas

Research map / 3D vision / Depth and stereo

EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors

Luca Bartolomei, Fabio Tosi, Matteo Poggi, Stefano Mattoccia, Guillermo Gallego

CVPR 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 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 DepthAnythingV2 depth regularizer to SVRaster (ablation)SVRaster NVS · ScanNet++ subsetdepth MAE (cm): 8.99 -> 6.61Improved
add MASt3R regularizer on top of all other regularizers (ablation)SVRaster NVS · ScanNet++ subsetdepth MAE (cm): 6.61 -> 38.71Hurt
add normal-consistency regularizers (with DAv2) (ablation)SVRaster NVS · ScanNet++ subsetdepth MAE (cm): 7.15 -> 6.57Improved
add asc and sparse regularizers (ablation)SVRaster NVS · ScanNet++ subsetdepth MAE (cm): 6.58 -> 6.57No clear effect
halve the normal regularizer weights (ablation)SVRaster NVS · ScanNet++ subsetdepth MAE (cm): 6.57 -> 6.38Improved
replace ambient-occlusion confidence with voxel-size confidence (ablation)EventHub NVS labels · ScanNet++ subset (threshold 0.85 vs 0.45)depth MAE (cm): 6.20 -> 6.03Improved
use SVRaster instead of Depth Anything v3 as rendering engine (ablation)EventHub MIX 3 SE-CFF · DSEC valMAE (px): 3.18 -> 1.01Improved
add ScanNet++ data to NeRF-Stereo data (MIX 1 to MIX 2) (ablation)E-FoundationStereo · DSEC valMAE (px): 1.39 -> 1.04Improved
add NeRF-Stereo and ScanNet++ to DSEC distilled data (MIX 3 to MIX 4) (ablation)SE-CFF · DSEC valMAE (px): 1.01 -> 1.07Hurt
add NeRF-Stereo and ScanNet++ to DSEC distilled data (MIX 3 to MIX 4) (ablation)E-FoundationStereo · M3ED DayMAE (px): 1.49 -> 0.98Improved
extend proxy-event synthetic data with TartanAir (ablation)EV-SceneFlow E-FoundationStereo · DSEC valMAE (px): 3.10 -> 1.76Improved
train with MIX 4 proxy labels instead of DSEC LiDAR labelsE-FoundationStereo · MVSEC DayMAE (px): 6.04 -> 1.33Improved

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