Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Pubblicazione: |
Zenodo
2026
|
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901926078054400 |
|---|---|
| author | Jaime Corsetti Davide Boscaini Fabio Poiesi |
| author_facet | Jaime Corsetti Davide Boscaini Fabio Poiesi |
| contents | <p>Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through<br>RANSAC-based algorithms or by directly regressing the pose with end-to-end optimisations. We argue that learning point-level discriminative features is overlooked in the<br>literature. To this end, we revisit Fully Convolutional Geometric Features (FCGF) and tailor it for object 6D pose estimation to achieve state-of-the-art performance. FCGF<br>employs sparse convolutions and learns point-level features using a fully-convolutional network by optimising a hardest contrastive loss. We can outperform recent competitors on popular benchmarks by adopting key modifications to the loss and to the input data representations, by carefully tuning the training strategies, and by employing data augmentations suitable for the underlying problem. We carry out a thorough ablation to study the contribution of each modification. The code is available at https://github.com/jcorsetti/FCGF6D.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18802809 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation Jaime Corsetti Davide Boscaini Fabio Poiesi <p>Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through<br>RANSAC-based algorithms or by directly regressing the pose with end-to-end optimisations. We argue that learning point-level discriminative features is overlooked in the<br>literature. To this end, we revisit Fully Convolutional Geometric Features (FCGF) and tailor it for object 6D pose estimation to achieve state-of-the-art performance. FCGF<br>employs sparse convolutions and learns point-level features using a fully-convolutional network by optimising a hardest contrastive loss. We can outperform recent competitors on popular benchmarks by adopting key modifications to the loss and to the input data representations, by carefully tuning the training strategies, and by employing data augmentations suitable for the underlying problem. We carry out a thorough ablation to study the contribution of each modification. The code is available at https://github.com/jcorsetti/FCGF6D.</p> |
| title | Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation |
| url | https://doi.org/10.5281/zenodo.18802809 |