AI Paper Atlas

Research map / Detection and segmentation / CNN features

TopoFuse: Topology-Aware Tri-Planar Fusion for 3D Cryo-Electron Tomography Segmentation

Rohit Kumar Salla, Neelesh Gupta, Xingjian Li, Min Xu

ECCV 2026 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 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 differentiable topology projection (T=5) (ablation)tri-planar + L_topo · EMPIAR-10499 ablationBE0: 2.41 -> 1.11Improved
add differentiable topology projection (T=5) (ablation)tri-planar + L_topo · EMPIAR-10499 ablationDice (%): 81.1 -> 85.2Improved
add Wasserstein topology loss without projection (ablation)tri-planar · EMPIAR-10499 ablationBE0: 2.88 -> 2.41Improved
add learned fusion without FiLM (ablation)tri-planar · EMPIAR-10499 ablationBE0: 3.10 -> 2.88Improved
add FiLM topology conditioning (ablation)TopoFuse · EMPIAR-10499 ablationBE0: 1.11 -> 1.10No clear effect
use learned topology prior instead of oracle at inference (ablation)TopoFuse · EMPIAR-10499 ablationBE0: 0.74 -> 1.09Hurt
increase projection steps from T=5 to T=10 (ablation)TopoFuse · EMPIAR-10499 ablationBE0: 1.11 -> 1.09No clear effect
reduce projection steps from T=5 to T=3 (ablation)TopoFuse · EMPIAR-10499 ablationBE0: 1.11 -> 1.21Hurt
TopoFuse vs BettiMatching soft lossTopoFuse (learned) · three cryo-ET benchmarks (mean)BE0: 2.68 -> 1.24Improved
TopoFuse vs BettiMatching soft lossTopoFuse (learned) · three cryo-ET benchmarks (mean)Dice (%): 80.3 -> 84.9Improved
non-differentiable PH post-processing instead of soft losstri-planar + TopoPost · EMD-0506Dice (%): 80.8 -> 79.0 Dice; BE0 2.29 -> 2.17Mixed
TopoFuse vs BettiMatching on synthetic noisy dataTopoFuse · SYN, SNR 0.10exact topology recovery (%): 61 -> 84Improved

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