AI Paper Atlas

Research map / Point clouds / Point cloud classification

3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds

Ryousuke Yamada, Kohsuke Ide, Yoshihiro Fukuhara, Hirokatsu Kataoka, Gilles Puy, Andrei Bursuc, Yuki M. Asano

CVPR 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 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 Z-axis alignment to RoomTours (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 51.8 -> 57.1Improved
add scale alignment to ScanNet scale distribution (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 55.5 -> 57.1Improved
add noise-regularized loss (Laplacian + consistency) (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 51.1 -> 57.1Improved
add Laplacian smoothing loss (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 55.0 -> 57.1Improved
add noise consistency loss (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 55.3 -> 57.1Improved
scale RoomTours from 1k to 49k scenesLAM3C · ScanNet semantic seg (LP)mIoU: 57.1 -> 65.9Improved
use pi3 instead of VGGT for reconstruction (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 49.3 -> 57.1Improved
use pi3 instead of MapAnything (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 50.1 -> 57.1Improved
use LAM3C instead of Sonata on clean ScanNet pre-trainingpre-training on ScanNet · ScanNet semantic seg (LP)mIoU: 67.1 vs 66.8No clear effect
use LAM3C instead of Sonata on noisy RoomTours-1kpre-training on RoomTours · ScanNet semantic seg (LP)mIoU: 51.1 -> 57.1Improved
include val/test scenes in Sonata pre-training (ablation)Sonata (ScanNet) · ScanNet semantic seg (Full-FT)mIoU: 75.4 -> 77.4Improved
kNN size k=24 vs k=8 for Laplacian graph (ablation)LAM3C · ScanNet semantic seg (LP)mIoU: 56.0 -> 57.1Mixed

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