Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2412.03259 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915901843963904 |
|---|---|
| author | Pedersen, Jens Egholm Korakovounis, Dimitris Conradt, Jörg |
| author_facet | Pedersen, Jens Egholm Korakovounis, Dimitris Conradt, Jörg |
| contents | Event-based vision sensors offer high time resolution, high dynamic range, and low power consumption, yet event-based vision models lag behind conventional frame-based vision methods. We argue that this gap is partly due to the lack of principled study of the transformation groups that govern event-based visual streams. Motivated by the role that geometric and group-theoretic methods have played in advancing computer vision, we present GERD: a simulator for generating event-based recordings of objects under precisely controlled affine, Galilean, and temporal scaling transformations. By providing ground-truth transformations at each timestep, GERD enables hypothesis-driven and controlled studies of geometric properties that are otherwise impossible to isolate in real-world datasets. The simulator supports three noise models and sub-pixel motion as a complement to real sensor datasets. We demonstrate its use in training and evaluating models with geometric guarantees and release GERD as an open tool available at github.com/ncskth/gerd |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03259 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GERD: Geometric event response data generation Pedersen, Jens Egholm Korakovounis, Dimitris Conradt, Jörg Computer Vision and Pattern Recognition Event-based vision sensors offer high time resolution, high dynamic range, and low power consumption, yet event-based vision models lag behind conventional frame-based vision methods. We argue that this gap is partly due to the lack of principled study of the transformation groups that govern event-based visual streams. Motivated by the role that geometric and group-theoretic methods have played in advancing computer vision, we present GERD: a simulator for generating event-based recordings of objects under precisely controlled affine, Galilean, and temporal scaling transformations. By providing ground-truth transformations at each timestep, GERD enables hypothesis-driven and controlled studies of geometric properties that are otherwise impossible to isolate in real-world datasets. The simulator supports three noise models and sub-pixel motion as a complement to real sensor datasets. We demonstrate its use in training and evaluating models with geometric guarantees and release GERD as an open tool available at github.com/ncskth/gerd |
| title | GERD: Geometric event response data generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03259 |