AI Paper Atlas

Research map / 3D vision / 3D generation

TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing

Tim-Felix Faasch, Jochen Kall, Jens Behley, Lucas Nunes, Cyrill Stachniss

ECCV 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 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
add equivariance/consistency loss to the TASE embedding (ablation)TASE · Feature reconstruction (held-out views)PSNR: 23.89 -> 24.64Improved
add equivariance/consistency loss to the TASE embedding (ablation)TASE · Feature reconstruction (held-out views)feature loss L_f: 0.1016 -> 0.0120Improved
add equivariance/consistency loss to the TASE embedding (ablation)TASE · Local 3D scene editingCLIP directional similarity: 0.0852 -> 0.1385Improved
add Difix3D+ finetuning of the editing diffusion model (ablation)TASE · Local 3D scene editingCLIP directional similarity: 0.1385 -> 0.1542Improved
add Difix3D+ finetuning to M_TASE without consistency loss (ablation)TASE · Local 3D scene editingCLIP directional similarity: 0.0852 -> 0.0905Improved
add Difix3D+ finetuning to PCA embedding (ablation)PCA baseline · Local 3D scene editingCLIP directional similarity: 0.1067 -> 0.1365Improved
use autoencoder embedding with consistency loss instead of PCA (ablation)TASE · Local 3D scene editingCLIP directional similarity: 0.1365 -> 0.1542Improved
use autoencoder embedding without consistency loss instead of PCA (ablation)TASE · Feature reconstruction (held-out views)feature loss L_f: 0.0879 -> 0.1016Hurt
use autoencoder embedding without consistency loss instead of PCA (ablation)TASE · Local 3D scene editingCLIP directional similarity: 0.1067 -> 0.0852Hurt
use TASE editing instead of DGETASE · Local 3D scene editinguser preference (geometry): 19.1% -> 64.3%Improved
use TASE editing instead of DGE on face sceneTASE · Face local editsCLIP directional similarity: 0.1181 -> 0.0965Hurt
retain fewer channels of the truncated embedding (2 vs 64) (ablation)TASE · 2D image generation with prompt 'in the snow'qualitative prompt adherence: 2 dims vs 64 dimsImproved

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