Search Results for author:
Found 50 papers, 21 papers with code
Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
Although these models have conventionally been evaluated for open-loop prediction, we show that they can be used to parameterize autoregressive closed-loop models without retraining.
3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
We marry diffusion policies and 3D scene representations for robot manipulation.
Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following
Diffusion-ES samples trajectories during evolutionary search from a diffusion model and scores them using a black-box reward function.
ODIN: A Single Model for 2D and 3D Perception
The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures.
Ranked #1 on
3D Instance Segmentation
on ScanNet200
Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
Our method, Diffusion-TTA, adapts pre-trained discriminative models such as image classifiers, segmenters and depth predictors, to each unlabelled example in the test set using generative feedback from a diffusion model.
Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models
We propose Generation to Simulation (Gen2Sim), a method for scaling up robot skill learning in simulation by automating generation of 3D assets, task descriptions, task decompositions and reward functions using large pre-trained generative models of language and vision.
Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models
Pre-trained and frozen large language models (LLMs) can effectively map simple scene rearrangement instructions to programs over a robot's visuomotor functions through appropriate few-shot example prompting.
Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models
This begs the question: can we re-purpose these large-scale pre-trained static image models for open-vocabulary video tracking?
Aligning Text-to-Image Diffusion Models with Reward Backpropagation
Due to their unsupervised training, controlling their behavior in downstream tasks, such as maximizing human-perceived image quality, image-text alignment, or ethical image generation, is difficult.
Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
3D perceptual representations are well suited for robot manipulation as they easily encode occlusions and simplify spatial reasoning.
Ranked #2 on
Robot Manipulation
on RLBench
Analogy-Forming Transformers for Few-Shot 3D Parsing
We present Analogical Networks, a model that encodes domain knowledge explicitly, in a collection of structured labelled 3D scenes, in addition to implicitly, as model parameters, and segments 3D object scenes with analogical reasoning: instead of mapping a scene to part segments directly, our model first retrieves related scenes from memory and their corresponding part structures, and then predicts analogous part structures for the input scene, via an end-to-end learnable modulation mechanism.
Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
Language is compositional; an instruction can express multiple relation constraints to hold among objects in a scene that a robot is tasked to rearrange.
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
We identify several challenges for fluid manipulation learning by evaluating a set of reinforcement learning and trajectory optimization methods on our platform.
Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
Effective planning of long-horizon deformable object manipulation requires suitable abstractions at both the spatial and temporal levels.
TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
We introduce TIDEE, an embodied agent that tidies up a disordered scene based on learned commonsense object placement and room arrangement priors.
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?
Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors.
Autonomous Vehicles
Bird's-Eye View Semantic Segmentation
+1
Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories
In this paper, we revisit Sand and Teller's "particle video" approach, and study pixel tracking as a long-range motion estimation problem, where every pixel is described with a trajectory that locates it in multiple future frames.
Test-time Adaptation with Slot-Centric Models
In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases.
Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds
We propose a language grounding model that attends on the referential utterance and on the object proposal pool computed from a pre-trained detector to decode referenced objects with a detection head, without selecting them from the pool.
Language Modulated Detection and Detection Modulated Language Grounding in 2D and 3D Scenes
Object detectors are typically trained on a fixed vocabulary of objects and attributes that is often too restrictive for open-domain language grounding, where the language utterance may refer to visual entities in various levels of abstraction, such as a cat, the leg of a cat, or the stain on the front leg of the chair.
CoCoNets: Continuous Contrastive 3D Scene Representations
This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos, agnostic to object and scene semantic content, and evaluates the resulting scene representations in the downstream tasks of visual correspondence, object tracking, and object detection.
Track, Check, Repeat: An EM Approach to Unsupervised Tracking
We propose an unsupervised method for detecting and tracking moving objects in 3D, in unlabelled RGB-D videos.
HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks
We propose HyperDynamics, a dynamics meta-learning framework that conditions on an agent's interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred properties of the dynamical system.
HyperDynamics: Generating Expert Dynamics Models by Observation
We propose HyperDynamics, a framework that conditions on an agent’s interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred properties of the dynamical system.
Move to See Better: Self-Improving Embodied Object Detection
Experiments on both indoor and outdoor datasets show that (1) our method obtains high-quality 2D and 3D pseudo-labels from multi-view RGB-D data; (2) fine-tuning with these pseudo-labels improves the 2D detector significantly in the test environment; (3) training a 3D detector with our pseudo-labels outperforms a prior self-supervised method by a large margin; (4) given weak supervision, our method can generate better pseudo-labels for novel objects.
3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
Object motion predictions are computed by a graph neural network that operates over the object features extracted from the 3D neural scene representation.
Disentangling 3D Prototypical Networks For Few-Shot Concept Learning
We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification.
3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
We can compare the 3D feature maps of two objects by searching alignment across scales and 3D rotations, and, as a result of the operation, we can estimate pose and scale changes without the need for 3D pose annotations.
Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping
We propose to leverage multiview data of \textit{static points} in arbitrary scenes (static or dynamic), to learn a neural 3D mapping module which produces features that are correspondable across time.
Epipolar Transformers
The intuition is: given a 2D location p in the current view, we would like to first find its corresponding point p' in a neighboring view, and then combine the features at p' with the features at p, thus leading to a 3D-aware feature at p. Inspired by stereo matching, the epipolar transformer leverages epipolar constraints and feature matching to approximate the features at p'.
Ranked #1 on
3D Hand Pose Estimation
on InterHand2.6M
Embodied Language Grounding with 3D Visual Feature Representations
We propose associating language utterances to 3D visual abstractions of the scene they describe.
Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping
Predictive coding theories suggest that the brain learns by predicting observations at various levels of abstraction.
Image Disentanglement and Uncooperative Re-Entanglement for High-Fidelity Image-to-Image Translation
Cross-domain image-to-image translation should satisfy two requirements: (1) preserve the information that is common to both domains, and (2) generate convincing images covering variations that appear in the target domain.
Learning Spatial Common Sense with Geometry-Aware Recurrent Networks
The proposed networks learn to "lift" and integrate 2D visual features over time into latent 3D feature maps of the scene.
Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions
We propose hand/eye con-trollers that learn to move the camera to keep the object within the field of viewand visible, in coordination to manipulating it to achieve the desired goal, e. g., pushing it to a target location.
Model Learning for Look-ahead Exploration in Continuous Control
We propose an exploration method that incorporates look-ahead search over basic learnt skills and their dynamics, and use it for reinforcement learning (RL) of manipulation policies .
Geometry-Aware Recurrent Neural Networks for Active Visual Recognition
We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations in the world scene and latent feature locations.
Reward Learning from Narrated Demonstrations
Humans effortlessly "program" one another by communicating goals and desires in natural language.
Depth-Adaptive Computational Policies for Efficient Visual Tracking
Current convolutional neural networks algorithms for video object tracking spend the same amount of computation for each object and video frame.
Self-supervised Learning of Motion Capture
In this work, we propose a learning based motion capture model for single camera input.
Ranked #2 on
3D Human Reconstruction
on Surreal
Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision
Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images' latent factors, or to other images, using supervised learning.
Motion Prediction Under Multimodality with Conditional Stochastic Networks
In this work, we present stochastic neural network architectures that handle such multimodality through stochasticity: future trajectories of objects, body joints or frames are represented as deep, non-linear transformations of random (as opposed to deterministic) variables.
SfM-Net: Learning of Structure and Motion from Video
We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations.
Learning Visual Predictive Models of Physics for Playing Billiards
The ability to plan and execute goal specific actions in varied, unexpected settings is a central requirement of intelligent agents.
Recurrent Network Models for Human Dynamics
We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture.
Ranked #8 on
Human Pose Forecasting
on Human3.6M
(MAR, walking, 1,000ms metric)
Human Pose Estimation with Iterative Error Feedback
Hierarchical feature extractors such as Convolutional Networks (ConvNets) have achieved impressive performance on a variety of classification tasks using purely feedforward processing.
Ranked #43 on
Pose Estimation
on MPII Human Pose
Learning to Segment Moving Objects in Videos
We segment moving objects in videos by ranking spatio-temporal segment proposals according to "moving objectness": how likely they are to contain a moving object.
Grouping-Based Low-Rank Trajectory Completion and 3D Reconstruction
Furthermore, NRSfM needs to be robust to noise in both segmentation and tracking, e. g., drifting, segmentation ``leaking'', optical flow ``bleeding'' etc.
Pose from Flow and Flow from Pose
The pose labeled segments and corresponding articulated joints are used to improve the motion flow fields by proposing kinematically constrained affine displacements on body parts.
