AI Paper Atlas

Research map / 3D vision / Depth and stereo

Enhanced Event-based Dense Stereo via Cross-Sensor Knowledge Distillation

Haihao Zhang, Yunjian Zhang, Jianing Li, Lin Zhu, Meng Lv, Yao Zhu, Yanwei Liu, Xiangyang Ji

ICCV 2025 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 3 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 feature distillation (shallow and deep) (ablation)IED2S · MVSEC split1mean disparity error (pix): 0.54 -> 0.38Improved
add feature distillation (ablation)IED2S · MVSEC split1/split3one-pixel accuracy: 91.0 -> 94.4Improved
add logit-level distillation alone (ablation)IED2S · MVSEC split1mean disparity error (pix): 0.54 -> 0.49Improved
add left-right consistency alone (ablation)IED2S · MVSEC split3one-pixel accuracy: 89.4 -> 90.3Improved
add LRC on top of F-distill (ablation)IED2S · MVSEC split1mean disparity error (pix): 0.38 -> 0.37Improved
add logit distillation on top of F-distill and LRC (ablation)IED2S · MVSEC split1mean disparity error (pix): 0.37 -> 0.32Improved
add all components (F-distill, L-distill, LRC) (ablation)IED2S · MVSEC split3one-pixel accuracy: 89.4 -> 93.4Improved
use proposed shallow distillation instead of plain MSE feature alignment (ablation)IED2S · MVSEC split1mean disparity error (pix): 0.45 -> 0.39Improved
add deep distillation to shallow distillation (ablation)IED2S · MVSEC split1mean disparity error (pix): 0.39 -> 0.32Improved
add distillation (full model vs none) (ablation)IED2S · MVSEC -> DSECMAE: 0.782 -> 0.563Improved
add distillation (full model vs none) (ablation)IED2S · DSEC -> MVSECone-pixel accuracy: 79.8 -> 91.4Improved
use intensity-to-event distillation vs best event-only method TESIED2S · MVSEC split1mean depth error (cm): 13.0 -> 11.2Improved

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