Metraipolis › archive › dc_ec6ef27a57eb

H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression — arXiv:2609.02684

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02684
License (as archived)
CC0-1.0
Archived
2026-10-17T04:25:02.370Z
SHA-256 of the archived text
29e3be3fc223ba6dd458f88bf38bd5cb78994c6a72901c5cffab954b2180f49c
Stable URL of this page
https://metraipolis.com/documento/dc_ec6ef27a57eb

How to cite

H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression — arXiv:2609.02684 — arXiv (en), https://arxiv.org/abs/2609.02684 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec6ef27a57eb (Metraipolis archive dc_ec6ef27a57eb, sha256 29e3be3fc223ba6dd458f88bf38bd5cb78994c6a72901c5cffab954b2180f49c)
BibTeX
@misc{dcec6ef27a57eb,
  title = {H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression — arXiv:2609.02684},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02684},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec6ef27a57eb; sha256 29e3be3fc223ba6dd458f88bf38bd5cb78994c6a72901c5cffab954b2180f49c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02684. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying 3D point cloud models on edge hardware such as the NVIDIA Jetson Orin Nano is severely constrained by compute and memory budgets. Existing compression methods require access to the model's original source code, rendering them inapplicable to the Open Neural Network Exchange (ONNX) binaries commonly distributed by vendors and model repositories. We present \textbf{H3DNAS}, a hardware-aware model compression framework that operates directly on ONNX computational graphs without requiring original source code, architecture class definition, or gradient access during search. H3DNAS makes three contributions: (1) a \textbf{Channel Dependency Graph (CDG)} that classifies ONNX operators into four constraint classes and formally establishes that the free parameter fraction $\rho_f$ is topological invariant, a provable compression ceiling computable in $\mathcal{O}(|V|+|E|)$; (2) a \textbf{Two-Stage Hierarchical Search} that prunes candidate architectures by $L_1$-importance channel selection, ranks them by output fidelity as a zero-shot label-free proxy, and applies GhostConv structural mutation to Pareto-optimal candidates; and (3) the \textbf{first source-code-free compression pipeline for 3D point cloud models}, operating entirely via ONNX graph surgery with no original architecture definition required. On ModelNet40, H3DNAS reduces the number of parameters in PointNet, PointNet++, and PointMLP by $65.5\%$, $43.2\%$, and $49.1\%$, respectively, while achieving $1.99\times$, $1.29\times$, and $1.67\times$ inference speedups with negligible loss in accuracy. The source code is publicly available\footnote{ this https URL }.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AR).
Categorie arXiv: Machine Learning (cs.LG) ; Hardware Architecture (cs.AR); Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.02684 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T03:29:02.884Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).