AI Paper Atlas

Research map / Point clouds / Point cloud classification

Deep Novel View Synthesis from Colored 3D Point Clouds

Zhenbo Song, Wayne Chen, Dylan Campbell, Hongdong Li

ECCV 2020 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 23 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 RefineNet to the coarse generator (ablation)Ours-coarse · NYU-V2 scene revealing (4096 points)PSNR: 14.275 -> 16.439Improved
add RefineNet to the coarse generator (ablation)Ours-coarse · NYU-V2 scene revealing (4096 points)MAE: 0.154 -> 0.117Improved
add RefineNet to the coarse generator (ablation)Ours-coarse · NYU-V2 scene revealing (4096 points)SSIM: 0.414 -> 0.566Improved
add RefineNet to the coarse generator (ablation)Ours-coarse · ICL-NUIM novel view synthesis (4096 points)PSNR: 15.6 -> 18.07Improved
add RefineNet to the coarse generator (ablation)Ours-coarse · ICL-NUIM novel view synthesis (4096 points)SSIM: 0.381 -> 0.579Improved
increase input points from 4096 to 8192 for refined model (ablation)Ours-refined · NYU-V2 scene revealingPSNR: 16.439 -> 16.266No clear effect
increase input points from 4096 to 8192 for refined model (ablation)Ours-refined · ICL-NUIM novel view synthesisPSNR: 18.07 -> 17.75No clear effect
increase input points from 4096 to 12288 for refined model (ablation)Ours-refined · NYU-V2 scene revealingMAE: 0.117 -> 0.125Hurt
use Ours-refined with 4096 points instead of invsfm using all pointsinvsfm · NYU-V2 scene revealingPSNR: 14.507 -> 16.439Improved
use Ours-refined with 4096 points instead of invsfm using all pointsinvsfm · ICL-NUIM novel view synthesisPSNR: 14.737 -> 18.07Improved
use point-cloud encoder instead of invsfm pipeline for inference speedinvsfm · inference timeseconds: 0.068 -> 0.038Improved

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