AI Paper Atlas

Research map / 3D vision / 3D generation

ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decomposition

Tianhao Wu, Chuanxia Zheng, Qianyi Wu, Tat-Jen Cham

ECCV 2024 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 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 clustering loss to ObjectSDF++ even with ground-truth instance labels (ablation)ObjectSDF++ · Replicaedge accuracy: 28.9 -> 58.9Improved
add clustering loss to ObjectSDF++ with GT labels (ablation)ObjectSDF++ · ReplicaPQ scene: 64.2 -> 69.1Improved
replace ObjectSDF++ opacity supervision with clustering method on Mask2Former labels (ablation)ObjectSDF++ · ReplicaPQ scene: 43.8 -> 59.2Improved
add regularization loss (variance of softmax values) (ablation)ClusteringSDF · ReplicaPQ scene: 52.6 -> 59.2Improved
add one-hot loss (ablation)ClusteringSDF · ReplicaPQ scene: 56.3 -> 59.2Improved
add foreground-background loss (ablation)ClusteringSDF · ReplicaPQ scene: 57.7 -> 59.2Improved
remove differentiation loss (ablation)ClusteringSDF · ReplicasegmentationHurt
add cross-view loss (ablation)ClusteringSDF · ScanNet/Replica instances never co-visibleinstance label assignmentImproved
use clustering loss instead of pixel-pair contrastive loss (Contrastive Lift)ClusteringSDF · ScanNet/Replicatraining time: >30h -> <8hImproved
use ClusteringSDF instead of Contrastive LiftScanNet · ScanNetPQ scene: 62.3 -> 61.0Hurt

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