AI Paper Atlas

Research map / Point clouds / Point cloud classification

PFGS: High Fidelity Point Cloud Rendering via Feature Splatting

Jiaxu Wang, Zhang Ziyi, Junhao He, Renjing Xu

ECCV 2024 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 7 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 two-stage training (pretrain Gaussian regressor before joint training) (ablation)PFGS · ScanNetPSNR: 15.92 -> 19.86Improved
add multiscale decoder (vs single-scale UNet) (ablation)PFGS · ScanNetPSNR: 18.27 -> 19.86Improved
add progressive loss terms (ablation)PFGS · ScanNetPSNR: 19.19 -> 19.86Improved
add multiscale loss terms (ablation)PFGS · ScanNetPSNR: 19.37 -> 19.86Improved
add frequency reconstruction loss L_mfr (ablation)PFGS · ScanNetLPIPS: 0.478 -> 0.452Improved
run decoder recurrently twice instead of once (ablation)PFGS · ScanNetPSNR: 19.19 -> 19.86Improved
increase decoder loops from 2 to 3 (ablation)PFGS · ScanNetPSNR: 19.86 -> 19.77No clear effect
train on dense points, test on sparse points (ablation)PFGS · DTU (train 1, test 0.2)PSNR: 12.78 vs 25.88 at matched densityHurt
increase test point count with model trained on 120k points (ablation)PFGS · THuman2.0PSNR: 31.60 -> 39.18Improved
replace Trivol (NeRF-based) with PFGS under added point noisepoint cloud renderer · THuman2.0 noise 3e-3PSNR: 20.04 -> 30.85Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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