AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

GPU-Accelerated Computation of Persistent Homology for Topological Analysis of Image Data

Fan Wang, Hubert Wagner, Rezaul Chowdhury, Chao Chen

TPAMI 2026 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 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
use TopoGPU instead of CRipserpersistent homology · all datasetsruntime speedup: average 53.24x, up to 198.01xImproved
use TopoGPU instead of best baselinepersistent homology · all datasetsruntime speedup: average 11.53x, up to 71.95xImproved
use GPU Morse matching without partitioning vs Morse complex boundary matrixTopoGPU · all datasetsboundary matrix size: 8.99x largerHurt
use discrete Morse complex instead of cubical complexTopoGPU · all datasetsboundary matrix size: 321.46x smallerImproved
use TopoSort instead of CPUKahntopological sort · 16 volumesspeedup: average 46.13x, up to 54.81xImproved
use TopoSort instead of GPUKahntopological sort · 16 volumesspeedup: 1.61x-9.80xImproved
larger matrix reduction shareTopoGPU · 16 volumestotal runtime: r = 0.64, rho = 0.62Hurt
use TopoGPU with low pair count volumesTopoGPU · small volumesbottleneck: Shockwave 78.76% path parityMixed

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