AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Online Multi-sensor Depth Fusion

Erik Sandström, Martin R. Oswald, Suryansh Kumar, Silvan Weder, Fisher Yu, Cristian Sminchisescu, Luc Van Gool

ECCV 2022 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 8 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 the extra loss terms beyond L_f (full loss) (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F-score (%): 62.65 -> 69.83Improved
use 2 3D conv layers in weighting network instead of none (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F1 (%): 48.57 -> 69.86Improved
increase 3D conv layers from 2 to 4 (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F1 (%): 69.86 -> 68.21No clear effect
add feature network (2D processing before unprojection) (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F-score (%): 67.44 -> 68.87Improved
add tanh normalization of weight counters (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F-score (%): 66.69 -> 68.92Improved
add feature grids to weights as weighting-network input (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F-score (%): 68.92 -> 69.83Improved
use 5 instead of 1 feature-network blocks (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F-score (%): 67.45 -> 68.39Mixed
vary feature dimension n from 2 to 5 (ablation)SenFuNet · Replica SGM+PSMNet ablation (no denoising)F-score (%): 68.86 -> 68.21No clear effect
add depth denoising network (ablation)SenFuNet · Replica ToF+PSMNet fusion (with denoising)F-score (%): 69.29 -> 76.47Improved
add depth denoising network (ablation)SenFuNet · Replica SGM+PSMNet fusion (with denoising)F-score (%): 69.83 -> 71.18Improved
late 3D fusion SenFuNet versus 2D Early Fusion with synchronized sensorsSenFuNet · Replica ToF+PSMNet fusion (with denoising)F-score (%): 74.60 -> 76.47Improved
lower ToF sampling rate from 1/2 to 1/3SenFuNet · Replica ToF+PSMNet time-asynchronous (ToF at 1/3 rate)F-score (%): Early Fusion 61.34 -> 55.52, SenFuNet 73.04 -> 74.93Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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