AI Paper Atlas

Research map / 3D vision / Depth and stereo

Stereo Depth Estimation with Echoes

Chenghao Zhang, Kun Tian, Bolin Ni, Gaofeng Meng, Bin Fan, Zhaoxiang Zhang, Chunhong Pan

ECCV 2022 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 9 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 CVR (cross-modal volume refinement) to stereo network (ablation)STEREO2DEPTH · Stereo-ReplicaRMSE: 0.248 -> 0.202Improved
add CVR (cross-modal volume refinement) to stereo network (ablation)STEREO2DEPTH · Stereo-Matterport3DRMSE: 0.636 -> 0.593Improved
add RDUE (relative depth uncertainty estimation) to stereo network (ablation)STEREO2DEPTH · Stereo-ReplicaRMSE: 0.248 -> 0.193Improved
add RDUE (relative depth uncertainty estimation) to stereo network (ablation)STEREO2DEPTH · Stereo-Matterport3DRMSE: 0.636 -> 0.599Improved
add RDUE on top of CVR (ablation)StereoEchoes · Stereo-ReplicaRMSE: 0.202 -> 0.186Improved
add CVR on top of RDUE (ablation)StereoEchoes · Stereo-ReplicaRMSE: 0.193 -> 0.186Improved
add RDUE on top of CVR (ablation)StereoEchoes · Stereo-Matterport3DRMSE: 0.593 -> 0.548Improved
add CVR on top of RDUE (ablation)StereoEchoes · Stereo-Matterport3DRMSE: 0.599 -> 0.548Improved
use CVR instead of concatenating audio and stereo features (ablation)StereoEchoes feature fusion · Stereo-ReplicaRMSE: 0.228 -> 0.202Improved
use CVR instead of bilinear transformation with attention (ablation)StereoEchoes feature fusion · Stereo-ReplicaRMSE: 0.234 -> 0.202Improved
use relative uncertainty instead of simple averaging for output fusion (ablation)StereoEchoes output fusion · Stereo-ReplicaRMSE: 0.281 -> 0.193Improved
use relative uncertainty instead of single-modal stereo uncertainty (ablation)StereoEchoes output fusion · Stereo-ReplicaRMSE: 0.234 -> 0.193Improved

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