AI Paper Atlas

Research map / 3D vision / Depth and stereo

SENSE: A Shared Encoder Network for Scene-Flow Estimation

Huaizu Jiang, Deqing Sun, Varun Jampani, Zhaoyang Lv, Erik Learned-Miller, Jan Kautz

ICCV 2019 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 82 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 flow and segmentation tasks to a shared encoder (ablation)SENSE disparity · KITTI 2015 40-image splitD1-occ: 2.73% -> 2.59%Improved
add disparity and segmentation tasks to a shared encoder (ablation)SENSE flow · KITTI 2015 40-image splitF1-occ: 11.37% -> 11.19%Improved
add flow and disparity tasks to a shared encoder (ablation)SENSE segmentation · KITTI 2015 40-image splitmIoU: 47.51% -> 48.25%Improved
share one encoder between flow and disparity instead of separate encoders (ablation)SENSE disparity · KITTI 2015D1-occ: 6.62% -> 6.38%Improved
share one encoder between flow and disparity instead of separate encoders (ablation)SENSE flow · KITTI 2015EPE vs F1-occ: EPE 6.37 -> 6.23; F1-occ 21.15% -> 23.29%Mixed
use 5 pyramid levels and add Batch Normalization (ablation)PWC-Net-style disparity decoder · FlyingThings3DEPE: 2.10 -> 1.61Improved
replace plain encoder with ResNet residual blocks (ablation)disparity decoder · FlyingThings3DEPE: 1.61 -> 1.40Improved
add Pyramid Pooling Module (ablation)disparity decoder · FlyingThings3DEPE: 1.40 -> 1.32Improved
add hourglass refinement module (ablation)disparity decoder · FlyingThings3DEPE: 1.32 -> 1.15Improved
add segmentation distillation loss (ablation)SENSE · KITTI 2015 40-image splitD1-occ: 2.52% -> 2.44%Improved
add occlusion distillation loss (ablation)SENSE · KITTI 2015 40-image splitD1-occ: 2.52% -> 2.38%Improved
add semantic, photometric and structural self-supervised losses (ablation)SENSE · KITTI 2015 40-image splitD1-occ: 2.52% -> 2.58%No clear effect

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