
-
Learning Portrait Style Representations
Style analysis of artwork in computer vision predominantly focuses on ac...
read it
-
Joint Estimation of Image Representations and their Lie Invariants
Images encode both the state of the world and its content. The former is...
read it
-
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Reinforcement learning is a powerful framework for robots to acquire ski...
read it
-
3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View
Automated capture of animal pose is transforming how we study neuroscien...
read it
-
TLIO: Tight Learned Inertial Odometry
In this work we propose a tightly-coupled Extended Kalman Filter framewo...
read it
-
Simple and Effective VAE Training with Calibrated Decoders
Variational autoencoders (VAEs) provide an effective and simple method f...
read it
-
Spin-Weighted Spherical CNNs
Learning equivariant representations is a promising way to reduce sample...
read it
-
Coherent Reconstruction of Multiple Humans from a Single Image
In this work, we address the problem of multi-person 3D pose estimation ...
read it
-
Planning to Explore via Self-Supervised World Models
Reinforcement learning allows solving complex tasks, however, the learni...
read it
-
Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks
Event-based cameras display great potential for a variety of conditions ...
read it
-
Action for Better Prediction
Good prediction is necessary for autonomous robotics to make informed de...
read it
-
Technical Report: Reactive Semantic Planning in Unexplored Semantic Environments Using Deep Perceptual Feedback
This paper presents a reactive planning system that enriches the topolog...
read it
-
Reactive Navigation in Partially Familiar Planar Environments Using Semantic Perceptual Feedback
This paper solves the planar navigation problem by recourse to an online...
read it
-
Learning Predictive Models From Observation and Interaction
Learning predictive models from interaction with the world allows an age...
read it
-
EventGAN: Leveraging Large Scale Image Datasets for Event Cameras
Event cameras provide a number of benefits over traditional cameras, suc...
read it
-
TexturePose: Supervising Human Mesh Estimation with Texture Consistency
This work addresses the problem of model-based human pose estimation. Re...
read it
-
TagSLAM: Robust SLAM with Fiducial Markers
TagSLAM provides a convenient, flexible, and robust way of performing Si...
read it
-
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop
Model-based human pose estimation is currently approached through two di...
read it
-
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
This paper addresses the problem of 3D human pose and shape estimation f...
read it
-
Event-based Vision: A Survey
Event cameras are bio-inspired sensors that work radically different fro...
read it
-
KeyIn: Discovering Subgoal Structure with Keyframe-based Video Prediction
Real-world image sequences can often be naturally decomposed into a smal...
read it
-
Equivariant Multi-View Networks
Several approaches to 3D vision tasks process multiple views of the inpu...
read it
-
Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform
In this work, we propose a novel transformation for events from an event...
read it
-
All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks
Image feature matching is a fundamental part of many geometric computer ...
read it
-
Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis
For recovering 3D object poses from 2D images, a prevalent method is to ...
read it
-
Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion
In this work, we propose a method that combines unsupervised deep learni...
read it
-
Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion
In this work, we propose a novel framework for unsupervised learning for...
read it
-
Cross-Domain 3D Equivariant Image Embeddings
Spherical convolutional networks have been introduced recently as tools ...
read it
-
Labeling Panoramas with Spherical Hourglass Networks
With the recent proliferation of consumer-grade 360 cameras, it is worth...
read it
-
Unsupervised Learning of Sensorimotor Affordances by Stochastic Future Prediction
Recently, much progress has been made building systems that can capture ...
read it
-
Ordinal Depth Supervision for 3D Human Pose Estimation
Our ability to train end-to-end systems for 3D human pose estimation fro...
read it
-
Learning to Estimate 3D Human Pose and Shape from a Single Color Image
This work addresses the problem of estimating the full body 3D human pos...
read it
-
Human Motion Capture Using a Drone
Current motion capture (MoCap) systems generally require markers and mul...
read it
-
Predicting the Future with Transformational States
An intelligent observer looks at the world and sees not only what is, bu...
read it
-
Realtime Time Synchronized Event-based Stereo
In this work, we propose a novel event based stereo method which address...
read it
-
EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras
Event-based cameras have shown great promise in a variety of situations ...
read it
-
The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception
Event based cameras are a new passive sensing modality with a number of ...
read it
-
Fast, Autonomous Flight in GPS-Denied and Cluttered Environments
One of the most challenging tasks for a flying robot is to autonomously ...
read it
-
Multi-Image Semantic Matching by Mining Consistent Features
This work proposes a multi-image matching method to estimate semantic co...
read it
-
3D object classification and retrieval with Spherical CNNs
3D object classification and retrieval presents many challenges that are...
read it
-
Polar Transformer Networks
Convolutional neural networks (CNNs) are inherently equivariant to trans...
read it
-
6-DoF Object Pose from Semantic Keypoints
This paper presents a novel approach to estimating the continuous six de...
read it
-
MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Recovering 3D full-body human pose is a challenging problem with many ap...
read it
-
Unsupervised learning of image motion by recomposing sequences
We propose a new method for learning a representation of image motion in...
read it
-
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
This paper addresses the challenge of 3D human pose estimation from a si...
read it
-
Fast, Robust, Continuous Monocular Egomotion Computation
We propose robust methods for estimating camera egomotion in noisy, real...
read it
-
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
This paper addresses the challenge of 3D full-body human pose estimation...
read it
-
Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
We investigate the problem of estimating the 3D shape of an object defin...
read it
-
Pose and Shape Estimation with Discriminatively Learned Parts
We introduce a new approach for estimating the 3D pose and the 3D shape ...
read it
-
3D Shape Estimation from 2D Landmarks: A Convex Relaxation Approach
We investigate the problem of estimating the 3D shape of an object, give...
read it