{"paper":{"title":"Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jianbo Shi, Jianqiao Wangni, Ji Liu, Kostas Daniilidis","submitted_at":"2018-12-29T06:23:11Z","abstract_excerpt":"For recovering 3D object poses from 2D images, a prevalent method is to pre-train an over-complete dictionary $\\mathcal D=\\{B_i\\}_i^D$ of 3D basis poses. During testing, the detected 2D pose $Y$ is matched to dictionary by $Y \\approx \\sum_i M_i B_i$ where $\\{M_i\\}_i^D=\\{c_i \\Pi R_i\\}$, by estimating the rotation $R_i$, projection $\\Pi$ and sparse combination coefficients $c \\in \\mathbb R_{+}^D$. In this paper, we propose non-convex regularization $H(c)$ to learn coefficients $c$, including novel leaky capped $\\ell_1$-norm regularization (LCNR), \\begin{align*} H(c)=\\alpha \\sum_{i } \\min(|c_i|,\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11295","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}