Retrieval-Combination Approach to Estimate 3D Human Pose from Monocular Image
スポンサーリンク
概要
- 論文の詳細を見る
A 3D human pose is estimated from a monocular image using a retrieval-combination approach that exploits the broad capability of example-based approaches and the flexibility of parts-based approaches. Instead of storing and searching for similar full-body examples, we adopt a half-body representation (i.e., either upper-body or lower-body) to reduce a large full-body database into a compact half-body database. The database can create millions of poses by valid half-body combinations. For a given query image, half-body candidates are first retrieved from the database by partial-shape matching. Valid half-body combinations of these candidates are selected based on a learned combination constraint, and then the optimal combination(s) is(are) chosen in a coarse-to-fine evaluation method. We show good experimental results for estimating poses with both synthetic and real images. Our approach has less time and space complexities than example-based approaches and ensures more realistic 3D pose estimates than those of parts-based approaches.
- Information and Media Technologies 編集運営会議の論文
Information and Media Technologies 編集運営会議 | 論文
- Optimal Balanced Semi-Matchings for Weighted Bipartite Graphs
- A Quantitative Evaluation Methodology of Interconnection Networks
- Proposal and Performance Evaluation of Hash-based Authentication for P2P Network
- Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases
- Ring Signatures: Universally Composable Definitions and Constructions