
-
Learning Temporal Dynamics from Cycles in Narrated Video
Learning to model how the world changes as time elapses has proven a cha...
read it
-
Language-Mediated, Object-Centric Representation Learning
We present Language-mediated, Object-centric Representation Learning (LO...
read it
-
Augmenting Policy Learning with Routines Discovered from a Demonstration
Humans can abstract prior knowledge from very little data and use it to ...
read it
-
Object-Centric Diagnosis of Visual Reasoning
When answering questions about an image, it not only needs knowing what ...
read it
-
Neural Radiance Flow for 4D View Synthesis and Video Processing
We present a method, Neural Radiance Flow (NeRFlow),to learn a 4D spatia...
read it
-
Object-Centric Neural Scene Rendering
We present a method for composing photorealistic scenes from captured im...
read it
-
pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
We have witnessed rapid progress on 3D-aware image synthesis, leveraging...
read it
-
Multi-Plane Program Induction with 3D Box Priors
We consider two important aspects in understanding and editing images: m...
read it
-
Learning 3D Dynamic Scene Representations for Robot Manipulation
3D scene representation for robot manipulation should capture three key ...
read it
-
Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection
A common dilemma in 3D object detection for autonomous driving is that h...
read it
-
Unsupervised Discovery of 3D Physical Objects from Video
We study the problem of unsupervised physical object discovery. Unlike e...
read it
-
End-to-End Optimization of Scene Layout
We propose an end-to-end variational generative model for scene layout s...
read it
-
Perspective Plane Program Induction from a Single Image
We study the inverse graphics problem of inferring a holistic representa...
read it
-
Learning Physical Graph Representations from Visual Scenes
Convolutional Neural Networks (CNNs) have proved exceptional at learning...
read it
-
When is Particle Filtering Efficient for POMDP Sequential Planning?
Particle filtering is a popular method for inferring latent states in st...
read it
-
Data Represention for Deep Learning with Priori Knowledge of Symmetric Wireless Tasks
Deep neural networks (DNNs) have been applied to address various wireles...
read it
-
Visual Grounding of Learned Physical Models
Humans intuitively recognize objects' physical properties and predict th...
read it
-
Visual Concept-Metaconcept Learning
Humans reason with concepts and metaconcepts: we recognize red and green...
read it
-
Look, Listen, and Act: Towards Audio-Visual Embodied Navigation
A crucial aspect of mobile intelligent agents is their ability to integr...
read it
-
Accurate Vision-based Manipulation through Contact Reasoning
Planning contact interactions is one of the core challenges of many robo...
read it
-
Proactive Optimization with Unsupervised Learning
Proactive resource allocation, say proactive caching at wireless edge, h...
read it
-
Entity Abstraction in Visual Model-Based Reinforcement Learning
This paper tests the hypothesis that modeling a scene in terms of entiti...
read it
-
Learning Compositional Koopman Operators for Model-Based Control
Finding an embedding space for a linear approximation of a nonlinear dyn...
read it
-
CLEVRER: CoLlision Events for Video REpresentation and Reasoning
The ability to reason about temporal and causal events from videos lies ...
read it
-
Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs
We present the DualSMC network that solves continuous POMDPs by learning...
read it
-
Program-Guided Image Manipulators
Humans are capable of building holistic representations for images at va...
read it
-
Neurally-Guided Structure Inference
Most structure inference methods either rely on exhaustive search or are...
read it
-
DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
We study the problem of learning physical object representations for rob...
read it
-
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that lear...
read it
-
Combining Physical Simulators and Object-Based Networks for Control
Physics engines play an important role in robot planning and control; ho...
read it
-
Unsupervised Discovery of Parts, Structure, and Dynamics
Humans easily recognize object parts and their hierarchical structure by...
read it
-
Stochastic Prediction of Multi-Agent Interactions from Partial Observations
We present a method that learns to integrate temporal information, from ...
read it
-
Learning to Infer and Execute 3D Shape Programs
Human perception of 3D shapes goes beyond reconstructing them as a set o...
read it
-
Learning to Reconstruct Shapes from Unseen Classes
From a single image, humans are able to perceive the full 3D shape of an...
read it
-
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Object-based factorizations provide a useful level of abstraction for in...
read it
-
Visual Object Networks: Image Generation with Disentangled 3D Representation
Recent progress in deep generative models has led to tremendous breakthr...
read it
-
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
We marry two powerful ideas: deep representation learning for visual rec...
read it
-
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
Real-life control tasks involve matter of various substances---rigid or ...
read it
-
ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
Physical simulators have been widely used in robot planning and control....
read it
-
Propagation Networks for Model-Based Control Under Partial Observation
There has been an increasing interest in learning dynamics simulators fo...
read it
-
MoSculp: Interactive Visualization of Shape and Time
We present a system that allows users to visualize complex human motion ...
read it
-
Physical Primitive Decomposition
Objects are made of parts, each with distinct geometry, physics, functio...
read it
-
Learning Shape Priors for Single-View 3D Completion and Reconstruction
The problem of single-view 3D shape completion or reconstruction is chal...
read it
-
Seeing Tree Structure from Vibration
Humans recognize object structure from both their appearance and motion;...
read it
-
3D-Aware Scene Manipulation via Inverse Graphics
We aim to obtain an interpretable, expressive and disentangled scene rep...
read it
-
3D Shape Perception from Monocular Vision, Touch, and Shape Priors
Perceiving accurate 3D object shape is important for robots to interact ...
read it
-
Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
An efficient, generalizable physical simulator with universal uncertaint...
read it
-
Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks
We study the problem of synthesizing a number of likely future frames fr...
read it
-
Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks
We propose a framework for the completely unsupervised learning of laten...
read it
-
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
We study 3D shape modeling from a single image and make contributions to...
read it