Can I read Park 等 - 2020 - LatentFusion End-To-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimati on EtoBox?

Park 等 - 2020 - LatentFusion End-To-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimati by linzhejiang001 is a document available to read on EtoBox.

What is Park 等 - 2020 - LatentFusion End-To-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimati about?

The document presents LatentFusion, an end-to-end differentiable framework for 6D object pose estimation that does not require 3D models or extensive training for unseen objects. It utilizes a neural network to reconstruct a latent 3D representation from a few reference images, allowing for pose estimation through gradient optimization. The method is evaluated on a new dataset, MOPED, and demonstrates competitive performance against supervised methods while being scalable to a large number of objects.

Author

linzhejiang001

Language

EN