Search Results for author:
Found 25 papers, 11 papers with code
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
We present a near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence, while simultaneously performing neural 3D reconstruction of the object.
MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner.
RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control
We present a system for collision-free control of a robot manipulator that uses only RGB views of the world.
Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
We present a parallelized optimization method based on fast Neural Radiance Fields (NeRF) for estimating 6-DoF pose of a camera with respect to an object or scene.
Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation
We propose a single-stage, category-level 6-DoF pose estimation algorithm that simultaneously detects and tracks instances of objects within a known category.
6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark
We propose a set of toy grocery objects, whose physical instantiations are readily available for purchase and are appropriately sized for robotic grasping and manipulation.
Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image
Prior work on 6-DoF object pose estimation has largely focused on instance-level processing, in which a textured CAD model is available for each object being detected.
NViSII: A Scriptable Tool for Photorealistic Image Generation
We present a Python-based renderer built on NVIDIA's OptiX ray tracing engine and the OptiX AI denoiser, designed to generate high-quality synthetic images for research in computer vision and deep learning.
Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera
We present a robotic grasping system that uses a single external monocular RGB camera as input.
Robotics
How to Close Sim-Real Gap? Transfer with Segmentation!
Combining the control policy learned from simulation with the perception model, we achieve an impressive $\bf{88\%}$ success rate in grasping a tiny sphere with a real robot.
Robotics
Importance Estimation for Neural Network Pruning
On ResNet-101, we achieve a 40% FLOPS reduction by removing 30% of the parameters, with a loss of 0. 02% in the top-1 accuracy on ImageNet.
Exact Gaussian Processes on a Million Data Points
Gaussian processes (GPs) are flexible non-parametric models, with a capacity that grows with the available data.
Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations
We present a system to infer and execute a human-readable program from a real-world demonstration.
Robotics
Improving Landmark Localization with Semi-Supervised Learning
First, we propose the framework of sequential multitasking and explore it here through an architecture for landmark localization where training with class labels acts as an auxiliary signal to guide the landmark localization on unlabeled data.
A Lightweight Approach for On-the-Fly Reflectance Estimation
In addition, we have created a large synthetic dataset, SynBRDF, which comprises a total of $500$K RGBD images rendered with a physically-based ray tracer under a variety of natural illumination, covering $5000$ materials and $5000$ shapes.
Pruning Convolutional Neural Networks for Resource Efficient Inference
We propose a new criterion based on Taylor expansion that approximates the change in the cost function induced by pruning network parameters.
Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
We introduce a hybrid CPU/GPU version of the Asynchronous Advantage Actor-Critic (A3C) algorithm, currently the state-of-the-art method in reinforcement learning for various gaming tasks.
Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network
Automatic detection and classification of dynamic hand gestures in real-world systems intended for human computer interaction is challenging as: 1) there is a large diversity in how people perform gestures, making detection and classification difficult; 2) the system must work online in order to avoid noticeable lag between performing a gesture and its classification; in fact, a negative lag (classification before the gesture is finished) is desirable, as feedback to the user can then be truly instantaneous.
Compressing Convolutional Neural Networks
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision.
Compressing Neural Networks with the Hashing Trick
As deep nets are increasingly used in applications suited for mobile devices, a fundamental dilemma becomes apparent: the trend in deep learning is to grow models to absorb ever-increasing data set sizes; however mobile devices are designed with very little memory and cannot store such large models.
Compressed Support Vector Machines
For most of the time during which we conducted this research, we were unaware of this prior work.
Image Data Compression for Covariance and Histogram Descriptors
Specifically, we show that we can reduce data sets to 16% and in some cases as little as 2% of their original size, while approximately matching the test error of kNN classification on the full training set.
Parallel Support Vector Machines in Practice
In particular, we provide the first comparison of algorithms with explicit and implicit parallelization.
Marginalizing Corrupted Features
In this paper, we propose a third, alternative approach to combat overfitting: we extend the training set with infinitely many artificial training examples that are obtained by corrupting the original training data.
Non-linear Metric Learning
On various benchmark data sets, we demonstrate these methods not only match the current state-of-the-art in terms of kNN classification error, but in the case of χ2-LMNN, obtain best results in 19 out of 20 learning settings.
