AI Paper Atlas

Research map / 3D vision / 3D generation

Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?

Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi, Laurent Caraffa, Flavian Vasile, Jeremie Mary, Andrew I. Comport, Valerie Gouet-Brunet

ICLR 2026 · 3D vision › 3D generation · approach: Learning physics from video · 0 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 Fused-Planes with shared base planes (vs Tri-Planes)Tri-Planes · ShapeNet (4 classes)training time (min): 64.32 -> 8.96Improved
share base planes and train in latent spaceTri-Planes · ShapeNet (4 classes)PSNR: 28.15 -> 30.47Improved
remove micro planes (ULW variant)Fused-Planes · ShapeNet (4 classes)per-object size (MB): 0.48 -> 0.0008Improved
use a set of base planes instead of M=1 (ablation)Fused-Planes · ShapeNet Cars (ablation)PSNR: 27.69 -> 28.64Improved
add macro planes (shared) in latent space (ablation)Fused-Planes · ShapeNet Cars (ablation)PSNR: 27.64 -> 28.64Improved
train in latent space rather than RGB (ablation)Fused-Planes · ShapeNet Cars (ablation)training time (min): 63.52 -> 8.92Improved
train in latent space rather than RGB (ablation)Fused-Planes · ShapeNet Cars (ablation)PSNR: 27.71 -> 28.64Improved
increase base planes from 50 to 75 (ablation)Fused-Planes · ShapeNet CarsPSNR: 30.27 -> 29.62Hurt
number of base planes M from 5 to 50 (ablation)Fused-Planes · ShapeNet CarsPSNR: 29.89 -> 30.27Improved
use low-budget randomly initialized VAE (ablation)Fused-Planes · ShapeNet CarsPSNR: 30.27 -> 29.22Hurt
train on 4 classes jointly instead of 1Fused-Planes · SpeakersPSNR: 29.99 -> 29.72Hurt
Fused-Planes vs K-Planes qualityK-Planes · ShapeNet (4 classes)PSNR: 30.88 -> 30.47Hurt

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