AI Paper Atlas

Research map / Point clouds / Point cloud classification

RPBG: Towards Robust Neural Point-based Graphics in the Wild

Qingtian Zhu, Zizhuang Wei, Zhongtian Zheng, Yifan Zhan, Zhuyu Yao, Jiawang Zhang, Kejian Wu, Yinqiang Zheng

ECCV 2024 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 5 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 Downgrade-aware Convolution (DAC) to the renderer (ablation)RPBG renderer · T&TPSNR: 21.88 -> 22.92Improved
add FFT loss (ablation)RPBG renderer · T&TSSIM: 0.769 -> 0.794 SSIM; PSNR 22.92 -> 22.94Improved
replace NPBG U-Net with restoration-style multi-scale fusion renderer (ablation)NPBG · T&TPSNR: 20.01 -> 21.88Improved
use multi-stage renderer instead of multi-scale fusion (ablation)RPBG renderer · T&Tmemory (GB): 12.67 -> 17.14 GB with PSNR 21.88 -> 21.75Hurt
use a learnable default feature vector for background instead of zeros (ablation)RPBG · Caterpillar (T&T)PSNR: 19.89 -> 21.78Improved
replace learnable vector with a 10^6-point sphere environment (ablation)RPBG · Caterpillar (T&T)PSNR: 21.78 -> 21.68No clear effect
add point cloud augmentation to SfM-initialized points (ablation)RPBG · Church (SfM init)PSNR: 21.41 -> 21.86Improved
add second round of point cloud augmentation (ablation)RPBG · Church (SfM init)PSNR: 21.86 -> 21.85No clear effect
use point-based re-rendering instead of RF-based methods on sparse-view scenesRPBG vs Gaussian Splatting · GigaMVSPSNR: 16.84 -> 20.54Improved
degrade triangulation from ground truth to random points (ablation)RPBG · triangulation configurationsPSNR: total drop of 3.29 dBHurt

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