Search Results for author:
Found 15 papers, 9 papers with code
NTrack: A Multiple-Object Tracker and Dataset for Infield Cotton Boll Counting
We show the efficacy of our approach on the task of tracking and counting infield cotton bolls.
IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstruction
Yet, such approaches often rely on distinguishing between the inside and outside of a surface in order to extract a zero level set when reconstructing the target.
CitDet: A Benchmark Dataset for Citrus Fruit Detection
Concretely, we provide high-resolution images of citrus trees located in an area known to be highly affected by HLB, along with high-quality bounding box annotations of citrus fruit.
LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction
We utilize global 2D features to predict a coarse shape of the target object and then use it as a base for higher-resolution reconstruction.
MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
Open-set recognition refers to the problem in which classes that were not seen during training appear at inference time.
Automated Reconstruction of 3D Open Surfaces from Sparse Point Clouds
Yet, these methods rely on a discretized representation of the raw data, which loses important surface details and can lead to outliers in the reconstruction.
Single Image Super-Resolution via a Dual Interactive Implicit Neural Network
To retrieve an image of a particular resolution, we apply a decoding function to a grid of locations each of which refers to the center of a pixel in the output image.
Evaluating Uncertainty Calibration for Open-Set Recognition
Despite achieving enormous success in predictive accuracy for visual classification problems, deep neural networks (DNNs) suffer from providing overconfident probabilities on out-of-distribution (OOD) data.
Variable Rate Compression for Raw 3D Point Clouds
In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data.
Thermal Image Super-Resolution Using Second-Order Channel Attention with Varying Receptive Fields
Specifically, we explore how to effectively attend to contrasting receptive fields (RFs) where increasing the RFs of a network can be computationally expensive.
An Uncertainty Estimation Framework for Probabilistic Object Detection
In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection.
Vision-Based Guidance for Tracking Dynamic Objects
In this paper, we present a novel vision-based framework for tracking dynamic objects using guidance laws based on a rendezvous cone approach.
Learning the Next Best View for 3D Point Clouds via Topological Features
In this paper, we introduce a reinforcement learning approach utilizing a novel topology-based information gain metric for directing the next best view of a noisy 3D sensor.
A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds
In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner.
Camera-Based Adaptive Trajectory Guidance via Neural Networks
In this paper, we introduce a novel method to capture visual trajectories for navigating an indoor robot in dynamic settings using streaming image data.
