AI Paper Atlas

Research map / 3D vision / Depth and stereo

StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction

Sameh Khamis, Sean Fanello, Christoph Rhemann, Adarsh Kowdle, Julien Valentin, Shahram Izadi

ECCV 2018 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 427 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 hierarchical multi-level refinement instead of a single refinement (8x) (ablation)StereoNet 8x · Scene FlowEPE all: 1.532 -> 1.101Improved
add hierarchical multi-level refinement instead of a single refinement (16x) (ablation)StereoNet 16x · Scene FlowEPE all: 1.974 -> 1.525Improved
use finer cost volume (8x instead of 16x) with multi refinement (ablation)StereoNet multi · Scene FlowEPE all: 1.525 -> 1.101Improved
use finer cost volume (8x instead of 16x) with single refinement (ablation)StereoNet single · Scene FlowEPE all: 1.974 -> 1.532Improved
add refinement to the 8x multi cost-volume output (ablation)StereoNet 8x multi · Scene FlowEPE all: 2.512 -> 1.101Improved
add refinement to the 8x single cost-volume output (ablation)StereoNet 8x single · Scene FlowEPE all: 2.486 -> 1.532Improved
add refinement to the 16x multi cost-volume output (ablation)StereoNet 16x multi · Scene FlowEPE all: 3.764 -> 1.525Improved
add refinement to the 16x single cost-volume output (ablation)StereoNet 16x single · Scene FlowEPE all: 3.558 -> 1.974Improved
use soft argmin instead of sampling-based probabilistic selection (ablation)StereoNet · Scene Flowconvergence and accuracyImproved
use unrefined 1/8 cost volume vs the prior full modelPrior method · Scene FlowEPE all: 2.51 -> 2.48Improved
use multi-scale 8x model vs CRLCRL · Scene FlowEPE all: 1.32 -> 1.1Improved
StereoNet vs state of the art on KITTI 2012Prior state of the art · KITTI 2012Out-Noc (%): 2.71 -> 4.91Hurt

Later papers that compared with this method

5 later accepted papers report StereoNet as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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