PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus
This addresses the need for faster multi-model fitting in 3D scene analysis, offering a significant speed improvement over iterative methods.
The paper tackles the problem of real-time robust estimation of multiple geometric models from noisy data by introducing a method that detects all model instances independently and in parallel, achieving state-of-the-art performance with inference times as low as five milliseconds per image.
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.