AI Paper Atlas

Research map / Video / Video segmentation and tracking

Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention

Weida Wang, Changyong He, Jin Zeng, Di Qiu

ICCV 2025 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 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 unrolled GLR module (single-frame) (ablation)GIGA-ToF baseline network · DVToF (synthetic test)MAE (m): 0.0409 -> 0.0357Improved
add unrolled GLR module (single-frame) (ablation)GIGA-ToF baseline network · DVToF (synthetic test)TEPE (m): 0.0793 -> 0.0734Improved
add depth-feature fusion across frames (ablation)GIGA-ToF with unrolled GLR · DVToF (synthetic test)MAE (m): 0.0357 -> 0.0238Improved
replace feature fusion with graph fusion (no attention) (ablation)GIGA-ToF · DVToF (synthetic test)MAE (m): 0.0238 -> 0.0219Improved
replace feature fusion with graph fusion (with attention) (ablation)GIGA-ToF · DVToF (synthetic test)TEPE (m): 0.0713 -> 0.0637Improved
add inter-frame attention to graph fusion (ablation)GIGA-ToF · DVToF (synthetic test)MAE (m): 0.0219 -> 0.0193Improved
add inter-frame attention to graph fusion (ablation)GIGA-ToF · DVToF (synthetic test)TEPE (m): 0.0702 -> 0.0637Improved
add inter-frame attention to feature fusion (ablation)GIGA-ToF with feature fusion · DVToF (synthetic test)MAE (m): 0.0238 -> 0.0214Improved
increase frame time step from 1 to 8 (ablation)GIGA-ToF · DVToF (synthetic test)MAE (m): 0.0190 -> 0.0210Hurt
increase frame time step from 1 to 2 (ablation)GIGA-ToF · DVToF (synthetic test)TEPE (m): 0.0634 -> 0.0608No clear effect
use multi-frame GIGA-ToF instead of best single-frame GLRUNGIGA-ToF vs GLRUN · DVToF (synthetic test)MAE (m): 0.0357 -> 0.0193Improved
use GIGA-ToF instead of WMF under augmented noiseGIGA-ToF vs WMF · DVToF with augmented noiseTEPE (m): 0.0950 -> 0.1102Hurt

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