English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent works on 6D object pose estimation focus on learning keypointcorrespondences between images and object models, and then determine the objectpose through RANSAC-based algorithms or by directly regressing the pose withend-to-end optimisations. We argue that learning point-level discriminativefeatures is overlooked in the literature. To this end, we revisit FullyConvolutional Geometric Features (FCGF) and tailor it for object 6D poseestimation to achieve state-of-the-art performance. FCGF employs sparseconvolutions and learns point-level features using a fully-convolutionalnetwork by optimising a hardest contrastive loss. We can outperform recentcompetitors on popular benchmarks by adopting key modifications to the loss andto the input data representations, by carefully tuning the training strategies,and by employing data augmentations suitable for the underlying problem. Wecarry out a thorough ablation to study the contribution of each modification.The code is available at https://github.com/jcorsetti/FCGF6D.

Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation