{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:40:15Z","timestamp":1773801615010,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Denoising Diffusion Probabilistic Models (DDPMs) have shown success in robust 3D object detection tasks. \nExisting methods often rely on the score matching from 3D boxes or pre-trained diffusion priors. However, they typically require multi-step iterations in inference, which limits efficiency.\nTo address this, we propose a Robust single-stage fully Sparse 3D object Detection Network with a Detachable Latent Framework (DLF) of DDPMs, named RSDNet. Specifically, RSDNet learns the denoising process in latent feature spaces through lightweight denoising networks like multi-level denoising autoencoders (DAEs). This enables RSDNet to effectively understand scene distributions under multi-level perturbations, achieving robust and reliable detection. Meanwhile, we reformulate the noising and denoising mechanisms of DDPMs, enabling DLF to construct multi-type and multi-level noise samples and targets, enhancing RSDNet robustness to multiple perturbations. Furthermore, a semantic-geometric conditional guidance is introduced  to perceive the object boundaries and shapes, alleviating the center feature missing problem in sparse representations,  enabling RSDNet to perform in a fully sparse detection pipeline. Moreover, the detachable denoising network design of DLF enables RSDNet to perform single-step detection in inference, further enhancing detection efficiency.  Extensive experiments on public benchmarks show that RSDNet can outperform existing methods, achieving state-of-the-art detection.<\/jats:p>","DOI":"10.1609\/aaai.v40i11.37819","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:46:35Z","timestamp":1773791195000},"page":"8668-8676","source":"Crossref","is-referenced-by-count":0,"title":["Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion"],"prefix":"10.1609","volume":"40","author":[{"given":"Wentao","family":"Qu","sequence":"first","affiliation":[]},{"given":"Guofeng","family":"Mei","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yujiao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xiaoshui","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37819\/41781","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37819\/41781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:46:35Z","timestamp":1773791195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i11.37819","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}