DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation

Wen，Yilin1; Li，Xiangyu2; Pan，Hao3; Yang，Lei1,4; Wang，Zheng5; Komura，Taku1; Wang，Wenping6

10.1007/978-3-031-20077-9_24

2022

17th European Conference on Computer Vision (ECCV)

0302-9743

1611-3349

978-3-031-20076-2

LECT NOTES ARTIF INT

13669 LNCS

404-421

OCT 23-27, 2022

null,Tel Aviv,ISRAEL

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects. Building on a well-known auto-encoding framework to cope with object symmetry and the lack of labeled training data, we achieve scalability by disentangling the latent representation of auto-encoder into shape and pose sub-spaces. The latent shape space models the similarity of different objects through contrastive metric learning, and the latent pose code is compared with canonical rotations for rotation retrieval. Because different object symmetries induce inconsistent latent pose spaces, we re-entangle the shape representation with canonical rotations to generate shape-dependent pose codebooks for rotation retrieval. We show state-of-the-art performance on two benchmarks containing textureless CAD objects without category and daily objects with categories respectively, and further demonstrate improved scalability by extending to a more challenging setting of daily objects across categories.

6D pose estimation Disentanglement Re-entanglement Scalability Sim-to-real Symmetry ambiguity

其他

英语

CPCI-S

Computer Science ; Imaging Science & Photographic Technology

Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology

WOS:000897132300024

2-s2.0-85142754501

Scopus

1.The University of Hong Kong,Hong Kong
2.Brown University,Providence,United States
3.Microsoft Research Asia,Beijing,China
4.Centre for Garment Production Limited,Hong Kong
5.SUSTech,Shenzhen,China
6.Texas A &M University,College Station,United States

Wen，Yilin,Li，Xiangyu,Pan，Hao,et al. DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:404-421.