AI Paper Atlas

Research map / Point clouds / Point cloud classification

IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation

Yun Wang, Cheng Chi, Min Lin, Xin Yang

ICCV 2023 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 6 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
basic cross-iteration refinement on streamlined baseline (ablation)Baseline-S · FlyingThings3DEPE3D (m): 0.0272 -> 0.0265No clear effect
add flow-guided refinement (downsample high-res flow to low-res warping) (ablation)Baseline-S + Basic-iter · FlyingThings3DEPE3D (m): 0.0265 -> 0.0247Improved
add feature-guided refinement (ablation)Baseline-S + Flow-guided · FlyingThings3DEPE3D (m): 0.0247 -> 0.0200Improved
add resampling scheme (ablation)Baseline-S + Flow-guided + Feature-guided · FlyingThings3DEPE3D (m): 0.0200 -> 0.0191Improved
add resampling scheme (ablation)IHNet · FlyingThings3Dinference time (ms): 110.71 -> 130.91Hurt
resample target points using previous scene flow (ablation)IHNet · FlyingThings3Dmean distance to Q_gt (m): 0.1543m -> 0.1084mImproved
increase test-time iterations beyond three (ablation)IHNet · FlyingThings3D and KITTIEPE3DMixed
IHNet versus WSAFlowNet on KITTI without fine-tuningIHNet · KITTI Scene FlowEPE3D (m): 0.0277 -> 0.0122Improved

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