AI Paper Atlas

Research map / Point clouds / Point cloud classification

Omni-scene Perception-oriented Point Cloud Geometry Enhancement for Coordinate Quantization

Wang Liu, Wei Gao

ICCV 2025 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 2 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 rooting step (ablation)rooting-growing-pruning network · ModelNet40 r1CD (x1e-2): 7.64 -> 4.47Improved
add growing step (ablation)rooting-growing-pruning network · ModelNet40 r1CD (x1e-2): 4.54 -> 4.47Improved
add pruning step (ablation)rooting-growing-pruning network · ModelNet40 r1CD (x1e-2): 6.57 -> 4.47Improved
add rooting step (ablation)rooting-growing-pruning network · ModelNet40 r1D1 PSNR (dB): 30.00 -> 36.86Improved
add rooting step (ablation)rooting-growing-pruning network · 8iVFB redandblack r1delta D1 PSNR (dB): 8.07 -> 10.39Improved
add pruning step (ablation)rooting-growing-pruning network · 8iVFB redandblack r1delta D1 PSNR (dB): 9.11 -> 10.39Improved
add pruning step (ablation)rooting-growing-pruning network · 8iVFB redandblack r1delta D2 PSNR (dB): 9.44 -> 8.74Hurt
add quantization-step loss Lq (ablation)rooting-growing-pruning network · ModelNet40 severe distortiondelta CD (x1e-2): 4.38 -> 4.49Improved
add quantization-step loss Lq (ablation)rooting-growing-pruning network · ShapeNet severe distortiondelta CD (x1e-2): 3.85 -> 4.02Improved
add quantization-step loss Lq (ablation)rooting-growing-pruning network · ScanObject severe distortiondelta CD (x1e-2): 3.49 -> 3.75Improved
add quantization-step loss Lq (ablation)rooting-growing-pruning network · 8iVFB soldier severe distortiondelta CD (x1e-2): 4.59 -> 4.73Improved
enhance G-PCC point clouds before DGCNN classificationDGCNN · ModelNet40 r1 classificationaccuracy (%): 9.44 -> 78.57Improved

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