SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.00151 · 2019

Multi-path Learning for Object Pose Estimation Across Domains

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce a scalable approach for object pose estimation trained on simulated RGB views of multiple 3D models together. We learn an encoding of object views that does not only describe an implicit orientation of all objects seen during training, but can also relate views of untrained objects. Our single-encoder-multi-decoder network is trained using a technique we denote "multi-path learning": While the encoder is shared by all objects, each decoder only reconstructs views of a single object. Consequently, views of different instances do not have to be separated in the latent space and can share common features. The resulting encoder generalizes well from synthetic to real data and across various instances, categories, model types and datasets. We systematically investigate the learned encodings, their generalization, and iterative refinement strategies on the ModelNet40 and T-LESS dataset. Despite training jointly on multiple objects, our 6D Object Detection pipeline achieves state-of-the-art results on T-LESS at much lower runtimes than competing approaches.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1908.00151")
get_code_for_paper("1908.00151")
have("1908.00151")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1908.00151.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1908.00151.svg)](https://syntology.ai/paper/1908.00151)

Connect an agent — have() is free.