AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Weight Space Representation Learning on Diverse NeRF Architectures

Francesco Ballerini, Pierluigi Zama Ramirez, Luigi Di Stefano, Samuele Salti

ICLR 2026 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 1 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 contrastive (SigLIP) loss to rendering loss (ablation)GMN encoder on ALL · cross-architecture classification (train MLP, test TRI)accuracy: 25.3 -> 58.6Improved
add contrastive loss to rendering loss (ablation)GMN encoder on ALL · cross-architecture classification (train TRI, test MLP)accuracy: 11.4 -> 77.8Improved
add contrastive loss to rendering loss (ablation)GMN encoder on ALL · ShapenetRender retrieval MLP/TRI Recall@1Recall@1 (%): 1.80 -> 30.62Improved
add contrastive loss to rendering loss (ablation)GMN encoder on ALL · Objaverse retrieval MLP/TRI Recall@10Recall@10 (%): 9.66 -> 33.65Improved
add contrastive loss to rendering loss (ablation)GMN encoder on ALL · classification, classifier trained on ALL, test MLPaccuracy: 93.6 -> 90.7Hurt
add contrastive loss to rendering loss (ablation)GMN encoder on ALL · unseen TRI-16W classificationaccuracy: 24.8 -> 72.1Improved
add contrastive loss to rendering loss (ablation)GMN encoder on ALL · unseen TRI-8C classification (classifier on ALL)accuracy: 69.4 -> 30.8Hurt
replace nf2vec with GMN encoder (rendering loss) on MLP NeRFsGMN encoder · ShapenetRender classification (MLP)accuracy: 92.1 -> 93.6Improved
replace tri-plane transformer of Cardace et al. with GMN encoderGMN encoder · ShapenetRender classification (TRI)accuracy: 93.1 -> 94.0Improved
use GMN encoder instead of nf2vec encoder in LLaNALLaNA · detailed captioning (MLP)S-BERT: 77.4 -> 74.1Hurt
use GMN encoder instead of nf2vec encoder in LLaNALLaNA · Q&A (MLP)S-BERT: 81.0 -> 81.0No clear effect
Cardace et al. vs GMN on unseen MLP-architecture changesTRI-2L/TRI-32H · unseen classificationaccuracy: 93.5 -> 92.6 (TRI-2L)Hurt

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