Details
| Original language | English |
|---|---|
| Pages (from-to) | 2804-2812 |
| Number of pages | 9 |
| Journal | Proceedings of the AAAI Conference on Artificial Intelligence |
| Volume | 38 |
| Issue number | 3 |
| Publication status | Published - 24 Mar 2024 |
| Event | 38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada Duration: 20 Feb 2024 → 27 Feb 2024 |
Abstract
We present a real-time method for robust estimation of multiple instances of geometric models from noisy data. Geometric models such as vanishing points, planar homographies or fundamental matrices are essential for 3D scene analysis. Previous approaches discover distinct model instances in an iterative manner, thus limiting their potential for speedup via parallel computation. In contrast, our method detects all model instances independently and in parallel. A neural network segments the input data into clusters representing potential model instances by predicting multiple sets of sample and inlier weights. Using the predicted weights, we determine the model parameters for each potential instance separately in a RANSAC-like fashion. We train the neural network via task-specific loss functions, i.e. we do not require a ground-truth segmentation of the input data. As suitable training data for homography and fundamental matrix fitting is scarce, we additionally present two new synthetic datasets. We demonstrate state-of-the-art performance on these as well as multiple established datasets, with inference times as small as five milliseconds per image.
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, No. 3, 24.03.2024, p. 2804-2812.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - PARSAC
T2 - 38th AAAI Conference on Artificial Intelligence, AAAI 2024
AU - Kluger, Florian
AU - Rosenhahn, Bodo
N1 - Publisher Copyright: Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2024/3/24
Y1 - 2024/3/24
N2 - We present a real-time method for robust estimation of multiple instances of geometric models from noisy data. Geometric models such as vanishing points, planar homographies or fundamental matrices are essential for 3D scene analysis. Previous approaches discover distinct model instances in an iterative manner, thus limiting their potential for speedup via parallel computation. In contrast, our method detects all model instances independently and in parallel. A neural network segments the input data into clusters representing potential model instances by predicting multiple sets of sample and inlier weights. Using the predicted weights, we determine the model parameters for each potential instance separately in a RANSAC-like fashion. We train the neural network via task-specific loss functions, i.e. we do not require a ground-truth segmentation of the input data. As suitable training data for homography and fundamental matrix fitting is scarce, we additionally present two new synthetic datasets. We demonstrate state-of-the-art performance on these as well as multiple established datasets, with inference times as small as five milliseconds per image.
AB - We present a real-time method for robust estimation of multiple instances of geometric models from noisy data. Geometric models such as vanishing points, planar homographies or fundamental matrices are essential for 3D scene analysis. Previous approaches discover distinct model instances in an iterative manner, thus limiting their potential for speedup via parallel computation. In contrast, our method detects all model instances independently and in parallel. A neural network segments the input data into clusters representing potential model instances by predicting multiple sets of sample and inlier weights. Using the predicted weights, we determine the model parameters for each potential instance separately in a RANSAC-like fashion. We train the neural network via task-specific loss functions, i.e. we do not require a ground-truth segmentation of the input data. As suitable training data for homography and fundamental matrix fitting is scarce, we additionally present two new synthetic datasets. We demonstrate state-of-the-art performance on these as well as multiple established datasets, with inference times as small as five milliseconds per image.
UR - http://www.scopus.com/inward/record.url?scp=85188931493&partnerID=8YFLogxK
U2 - 10.1609/aaai.v38i3.28060
DO - 10.1609/aaai.v38i3.28060
M3 - Conference article
AN - SCOPUS:85188931493
VL - 38
SP - 2804
EP - 2812
JO - Proceedings of the AAAI Conference on Artificial Intelligence
JF - Proceedings of the AAAI Conference on Artificial Intelligence
SN - 2159-5399
IS - 3
Y2 - 20 February 2024 through 27 February 2024
ER -