AI Paper Atlas

Research map / Point clouds / Segmentation and detection

TACO-Net: Topological Signatures Triumph in 3D Object Classification

Anirban Ghosh, Ayan Dutta

ECCV 2026 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 2 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 density/erosion/dilation/signed-distance features to height features (ablation)TACO-Net · ModelNet40overall accuracy: 98.29 -> 98.82Improved
add radial filtrations to DEDS + height (ablation)TACO-Net · ModelNet40overall accuracy: 98.82 -> 99.05Improved
add height filtration to DEDS features (ablation)TACO-Net · ModelNet40overall accuracy: 96.52 -> 98.82Improved
add amplitude features to entropy-only vectors (ablation)TACO-Net · ModelNet40overall accuracy: 96.16 -> 99.05Improved
add third Conv1D layer (ablation)TACO-Net 1D CNN · ModelNet40overall accuracy: 98.18 -> 99.05Improved
add second and third Conv1D layers to a single layer (ablation)TACO-Net 1D CNN · ModelNet40overall accuracy: 94.76 -> 99.05Improved
use voxel size 0.05 instead of 0.03 (ablation)TACO-Net · ModelNet40overall accuracy: 98.61 -> 99.05Improved
use voxel size 0.05 instead of 0.07 (ablation)TACO-Net · ModelNet40overall accuracy: 98.30 -> 99.05Improved
replace 1D CNN with 2.2M-parameter transformer (ablation)TACO-Net · ModelNet40overall accuracy: 99.05 -> 62.20Hurt
replace 1D CNN with XGBoost (ablation)TACO-Net · ModelNet40overall accuracy: 99.05 -> 81.35Hurt
replace 1D CNN with Random Forest (ablation)TACO-Net · ModelNet40overall accuracy: 99.05 -> 78.35Hurt
add corrupted-copy augmentation for 20% of training data (ablation)TACO-Net · ModelNet40-C high rotationoverall accuracy: 49.39 -> 96.11Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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