Object-Pose Estimation With Neural Population Codes
Robotic assembly tasks require object-pose estimation, particularly for tasks that avoid costly mechanical constraints. Object symmetry complicates the direct mapping of sensory input to object rotation, as the rotation becomes ambiguous and lacks a unique training target. Some proposed solutions involve evaluating multiple pose hypotheses against the input or predicting a probability distribution, but these approaches suffer from significant computational overhead. Here, we show that representing object rotation with a neural population code overcomes these limitations, enabling a direct mapping to rotation and end-to-end learning. As a result, population codes facilitate fast and accurate pose estimation. On the T-LESS dataset, we achieve inference in 3.2 milliseconds on an Apple M1 CPU and a Maximum Symmetry-Aware Surface Distance accuracy of 84.7% using only gray-scale image input, compared to 69.7% accuracy when directly mapping to pose.
Code (0)
등록된 구현이 없습니다.
Tasks
CPUObjectPose EstimationSimilar Papers 제목 키워드 기반
Advantages of Neural Population Coding for Deep Learning
Scalar variables, e.g., the orientation of a shape in an image, are commonly predicted using a single output neuron in a neural network. In contrast, the mammalian cortex represents variables with a population of neurons…
Deep LearningStochastic Image Deformation in Frequency Domain and Parameter Estimation using Moment Evolutions
Modelling deformation of anatomical objects observed in medical images can help describe disease progression patterns and variations in anatomy across populations. We apply a stochastic generalisation of the Large Deform…
Anatomyparameter estimationDynamical Mechanism of Sampling-based Stochastic Inference under Probabilistic Population Codes
Animals are known to make efficient probabilistic inferences based on uncertain and noisy information from the outside world. Although it is known that generic neural networks can perform near-optimal point estimation by…
Inductive BiasOptimal prior-dependent neural population codes under shared input noise
The brain uses population codes to form distributed, noise-tolerant representations of sensory and motor variables. Recent work has examined the theoretical optimality of such codes in order to gain insight into the prin…
Neurometric function analysis of population codes
The relative merits of different population coding schemes have mostly been analyzed in the framework of stimulus reconstruction using Fisher Information. Here, we consider the case of stimulus discrimination in a two al…