AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Click-Gaussian: Interactive Segmentation to Any 3D Gaussians

Seokhun Choi, Hyeonseop Song, Jaechul Kim, Taehyeong Kim, Hoseok Do

ECCV 2024 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 54 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 Global Feature-guided Learning loss (ablation)Click-Gaussian · LERF-Mask fine levelmIoU: 42.3 -> 84.3Improved
add GFL loss (ablation)Click-Gaussian · LERF-Mask all objectsmIoU: 58.6 -> 85.4Improved
add granularity prior (fine feature includes coarse feature) (ablation)Click-Gaussian · LERF-Mask fine levelmIoU: 78.3 -> 84.3Improved
add hypersphere (3D-norm) regularization (ablation)Click-Gaussian · LERF-Mask fine levelmIoU: 74.1 -> 84.3Improved
add spatial consistency regularization (ablation)Click-Gaussian · LERF-Mask fine levelmIoU: 78.5 -> 84.3Improved
add rendered feature (2D-norm) regularization (ablation)Click-Gaussian · LERF-Mask coarse levelmIoU: 89.3 -> 89.1 coarse; 80.8 -> 84.3 fineMixed
use two-level masks instead of three-level-area masks (ablation)Click-Gaussian · LERF-MaskmIoUImproved
assign fine mask by smallest segment (area) instead of highest score segment (ablation)three-level masks · LERF-Mask fine levelmIoUImproved
Click-Gaussian versus GARField on Ramen fine levelClick-Gaussian · LERF-Mask Ramen finemIoU: 86.9 (GARField) vs 86.7No clear effect
replace SAM-decoder and post-processing methods with feature-field clustersClick-Gaussian · SPIn-NeRFmIoU: 88.0 -> 94.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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