2.3k citations · 4.5k across the 63 of their papers we have counts for
71 papers
EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks
Ziyun Wang, Fernando Cladera Ojeda, Anthony Bisulco +6
Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to sta…
EvAC3D: From Event-based Apparent Contours to 3D Models via Continuous Visual Hulls
Ziyun Wang, Kenneth Chaney, Kostas Daniilidis
3D reconstruction from multiple views is a successful computer vision field with multiple deployments in applications. State of the art is based on traditional RGB frames that enab…
Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE
Wen Jiang, Kostas Daniilidis
We propose a novel method for 3D shape completion from a partial observation of a point cloud. Existing methods either operate on a global latent code, which limits the expressiven…
Equivariant Light Field Convolution and Transformer
Yinshuang Xu, Jiahui Lei, Kostas Daniilidis
3D reconstruction and novel view rendering can greatly benefit from geometric priors when the input views are not sufficient in terms of coverage and inter-view baselines. Deep lea…
Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces
Yinshuang Xu, Jiahui Lei, Edgar Dobriban +1
We introduce a unified framework for group equivariant networks on homogeneous spaces derived from a Fourier perspective. We consider tensor-valued feature fields, before and after…
SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space
Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Edgar Dobriban +1
We propose a method for 3D shape reconstruction from unoriented point clouds. Our method consists of a novel SE(3)-equivariant coordinate-based network (TF-ONet), that parametrizes…
CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism
Jiahui Lei, Kostas Daniilidis
While neural representations for static 3D shapes are widely studied, representations for deformable surfaces are limited to be template-dependent or lack efficiency. We introduce…
Learning Augmentation Distributions using Transformed Risk Minimization
Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Kostas Daniilidis +1
We propose a new \emph{Transformed Risk Minimization} (TRM) framework as an extension of classical risk minimization. In TRM, we optimize not only over predictive models, but also…
Single-Camera 3D Head Fitting for Mixed Reality Clinical Applications
Tejas Mane, Aylar Bayramova, Kostas Daniilidis +2
We address the problem of estimating the shape of a person's head, defined as the geometry of the complete head surface, from a video taken with a single moving camera, and determi…
Probabilistic Modeling for Human Mesh Recovery
Nikos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman +1
This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty…
Learning to Map for Active Semantic Goal Navigation
Georgios Georgakis, Bernadette Bucher, Karl Schmeckpeper +2
We consider the problem of object goal navigation in unseen environments. Solving this problem requires learning of contextual semantic priors, a challenging endeavour given the sp…
Deformable Linear Object Prediction Using Locally Linear Latent Dynamics
Wenbo Zhang, Karl Schmeckpeper, Pratik Chaudhari +1
We propose a framework for deformable linear object prediction. Prediction of deformable objects (e.g., rope) is challenging due to their non-linear dynamics and infinite-dimension…
Learning Portrait Style Representations
Sadat Shaik, Bernadette Bucher, Nephele Agrafiotis +3
Style analysis of artwork in computer vision predominantly focuses on achieving results in target image generation through optimizing understanding of low level style characteristi…
Joint Estimation of Image Representations and their Lie Invariants
Christine Allen-Blanchette, Kostas Daniilidis
Images encode both the state of the world and its content. The former is useful for tasks such as planning and control, and the latter for classification. The automatic extraction…
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Karl Schmeckpeper, Oleh Rybkin, Kostas Daniilidis +2
Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is d…
3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View
Marc Badger, Yufu Wang, Adarsh Modh +5
Automated capture of animal pose is transforming how we study neuroscience and social behavior. Movements carry important social cues, but current methods are not able to robustly…
TLIO: Tight Learned Inertial Odometry
Wenxin Liu, David Caruso, Eddy Ilg +5
In this work we propose a tightly-coupled Extended Kalman Filter framework for IMU-only state estimation. Strap-down IMU measurements provide relative state estimates based on IMU…
Planning to Explore via Self-Supervised World Models
Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis +3
Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-…
Coherent Reconstruction of Multiple Humans from a Single Image
Wen Jiang, Nikos Kolotouros, Georgios Pavlakos +2
In this work, we address the problem of multi-person 3D pose estimation from a single image. A typical regression approach in the top-down setting of this problem would first detec…
Simple and Effective VAE Training with Calibrated Decoders
Oleh Rybkin, Kostas Daniilidis, Sergey Levine
Variational autoencoders (VAEs) provide an effective and simple method for modeling complex distributions. However, training VAEs often requires considerable hyperparameter tuning…
Spin-Weighted Spherical CNNs
Carlos Esteves, Ameesh Makadia, Kostas Daniilidis
Learning equivariant representations is a promising way to reduce sample and model complexity and improve the generalization performance of deep neural networks. The spherical CNNs…
Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks
Chankyu Lee, Adarsh Kumar Kosta, Alex Zihao Zhu +3
Event-based cameras display great potential for a variety of tasks such as high-speed motion detection and navigation in low-light environments where conventional frame-based camer…
An Adversarial Objective for Scalable Exploration
Bernadette Bucher, Karl Schmeckpeper, Nikolai Matni +1
Model-based curiosity combines active learning approaches to optimal sampling with the information gain based incentives for exploration presented in the curiosity literature. Exis…
Reactive Navigation in Partially Familiar Planar Environments Using Semantic Perceptual Feedback
Vasileios Vasilopoulos, Georgios Pavlakos, Karl Schmeckpeper +2
This paper solves the planar navigation problem by recourse to an online reactive scheme that exploits recent advances in SLAM and visual object recognition to recast prior geometr…