AI Paper Atlas

Research map / Point clouds / Point cloud classification

A Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D

Tianyi Liu, Sen He, Vinodh Kumaran Jayakumar, Wei Wang

ECCV 2022 · 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
train application-specific models instead of one general model (ablation)Coarse-to-Fine (large) · Cloud 3D gaming imagesPSNR at same bitrate: 2 to 4dBImproved
slim and app-specific model on Imhotep datasetCoarse-to-Fine · Imhotepbitrate at 36 dB PSNR: saved about 0.3 bpp with a PSNR of 36dBImproved
reduce channels from Large to Medium (ablation)app-specific Coarse-to-Fine · Cloud 3D gaming imagescompression time (s): 4.16 -> 2.24Improved
reduce channels from Medium to Small (ablation)app-specific Coarse-to-Fine · Cloud 3D gaming imagescompression time (s): 2.24 -> 1.63Improved
reduce channels from Small to XSmall (ablation)app-specific Coarse-to-Fine · Cloud 3D gaming imagesrate-distortionHurt
reduce channels from Small to XSmall (ablation)app-specific Coarse-to-Fine · Cloud 3D gaming imagescompression time (s): 1.63 -> 1.43Improved
add Model-Task Balance (larger input tiles) to Small model (ablation)Small model · Cloud 3D gaming imagescompression time (s): 1.63 -> 0.93Improved
add Model-Task Balance (larger input tiles) to Small model (ablation)Small model · Cloud 3D gaming imagesdecompression time (s): 2.60 -> 1.75Improved
prune the last hyperprior layer (ha2/hs2) (ablation)Small model with M-T-Balance · Cloud 3D gaming imagescompression time (s): 0.93 -> 0.74Improved
prune the last hyperprior layer (ha2/hs2) (ablation)Small model with M-T-Balance · Cloud 3D gaming imagesrate-distortionNo clear effect
slim application-specific model replaces Coarse-to-FineCoarse-to-Fine · Cloud 3D gaming imagescompression time (s): 6.52 -> 0.74Improved
slim application-specific model replaces Coarse-to-FineCoarse-to-Fine · Cloud 3D gaming imagesdecompression time (s): 7.72 -> 1.64Improved

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