b'Jia Deng'

research

∙ 06/15/2023

Infinite Photorealistic Worlds using Procedural Generation

We introduce Infinigen, a procedural generator of photorealistic 3D scen...

0 Alexander Raistrick, et al. ∙

research

∙ 08/08/2022

Label-Free Synthetic Pretraining of Object Detectors

We propose a new approach, Synthetic Optimized Layout with Instance Dete...

0 Hei Law, et al. ∙

research

∙ 08/08/2022

Deep Patch Visual Odometry

We propose Deep Patch Visual Odometry (DPVO), a new deep learning system...

0 Zachary Teed, et al. ∙

research

∙ 05/25/2022

Generating Natural Language Proofs with Verifier-Guided Search

Deductive reasoning (drawing conclusions from assumptions) is a challeng...

0 Kaiyu Yang, et al. ∙

research

∙ 05/12/2022

View Synthesis with Sculpted Neural Points

We address the task of view synthesis, which can be posed as recovering ...

6 Yiming Zuo, et al. ∙

research

∙ 05/09/2022

Multiview Stereo with Cascaded Epipolar RAFT

We address multiview stereo (MVS), an important 3D vision task that reco...

0 Zeyu Ma, et al. ∙

research

∙ 04/26/2022

Coupled Iterative Refinement for 6D Multi-Object Pose Estimation

We address the task of 6D multi-object pose: given a set of known 3D obj...

7 Lahav Lipson, et al. ∙

research

∙ 02/01/2022

IFOR: Iterative Flow Minimization for Robotic Object Rearrangement

Accurate object rearrangement from vision is a crucial problem for a wid...

6 Ankit Goyal, et al. ∙

research

∙ 11/23/2021

Learning Symbolic Rules for Reasoning in Quasi-Natural Language

Symbolic reasoning, rule-based symbol manipulation, is a hallmark of hum...

0 Kaiyu Yang, et al. ∙

research

∙ 10/14/2021

Non-deep Networks

Depth is the hallmark of deep neural networks. But more depth means more...

0 Ankit Goyal, et al. ∙

research

∙ 09/15/2021

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

We introduce RAFT-Stereo, a new deep architecture for rectified stereo b...

0 Lahav Lipson, et al. ∙

research

∙ 08/24/2021

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SL...

0 Zachary Teed, et al. ∙

research

∙ 06/16/2021

Dynamically Grown Generative Adversarial Networks

Recent work introduced progressive network growing as a promising way to...

0 Lanlan Liu, et al. ∙

research

∙ 06/09/2021

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline

Processing point cloud data is an important component of many real-world...

0 Ankit Goyal, et al. ∙

research

∙ 03/22/2021

Tangent Space Backpropagation for 3D Transformation Groups

We address the problem of performing backpropagation for computation gra...

0 Zachary Teed, et al. ∙

research

∙ 03/10/2021

A Study of Face Obfuscation in ImageNet

Face obfuscation (blurring, mosaicing, etc.) has been shown to be effect...

8 Kaiyu Yang, et al. ∙

research

∙ 12/03/2020

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Understanding spatial relations (e.g., "laptop on table") in visual inpu...

1 Ankit Goyal, et al. ∙

research

∙ 12/01/2020

RAFT-3D: Scene Flow using Rigid-Motion Embeddings

We address the problem of scene flow: given a pair of stereo or RGB-D vi...

0 Zachary Teed, et al. ∙

research

∙ 11/03/2020

Rearrangement: A Challenge for Embodied AI

We describe a framework for research and evaluation in Embodied AI. Our ...

2 Dhruv Batra, et al. ∙

research

∙ 10/27/2020

Strongly Incremental Constituency Parsing with Graph Neural Networks

Parsing sentences into syntax trees can benefit downstream applications ...

0 Kaiyu Yang, et al. ∙

research

∙ 07/29/2020

Learning Video Representations from Textual Web Supervision

Videos found on the Internet are paired with pieces of text, such as tit...

5 Jonathan C. Stroud, et al. ∙

research

∙ 07/27/2020

A Unified Framework of Surrogate Loss by Refactoring and Interpolation

We introduce UniLoss, a unified framework to generate surrogate losses f...

0 Lanlan Liu, et al. ∙

research

∙ 07/26/2020

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild

Single-view 3D is the task of recovering 3D properties such as depth and...

30 Weifeng Chen, et al. ∙

research

∙ 07/21/2020

PackIt: A Virtual Environment for Geometric Planning

The ability to jointly understand the geometry of objects and plan actio...

12 Ankit Goyal, et al. ∙

research

∙ 03/31/2020

How Useful is Self-Supervised Pretraining for Visual Tasks?

Recent advances have spurred incredible progress in self-supervised pret...

3 Alejandro Newell, et al. ∙

research

∙ 03/26/2020

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep net...

3 Zachary Teed, et al. ∙

research

∙ 02/17/2020

Learning to Prove Theorems by Learning to Generate Theorems

We consider the task of automated theorem proving, a key AI task. Deep l...

37 Mingzhe Wang, et al. ∙

research

∙ 12/16/2019

Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy

Computer vision technology is being used by many but remains representat...

9 Kaiyu Yang, et al. ∙

research

∙ 12/04/2019

Compositional Temporal Visual Grounding of Natural Language Event Descriptions

Temporal grounding entails establishing a correspondence between natural...

6 Jonathan C. Stroud, et al. ∙

research

∙ 10/16/2019

Generative Modeling for Small-Data Object Detection

This paper explores object detection in the small data regime, where onl...

18 Lanlan Liu, et al. ∙

research

∙ 08/20/2019

Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control

Recent progress on physics-based character animation has shown impressiv...

6 Yu-Wei Chao, et al. ∙

research

∙ 08/12/2019

Feature Partitioning for Efficient Multi-Task Architectures

Multi-task learning holds the promise of less data, parameters, and time...

4 Alejandro Newell, et al. ∙

research

∙ 08/07/2019

SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Understanding the spatial relations between objects in images is a surpr...

1 Kaiyu Yang, et al. ∙

research

∙ 07/26/2019

To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments

In this paper we compare learning-based methods and classical methods fo...

3 Noriyuki Kojima, et al. ∙

research

∙ 06/29/2019

Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

Synthetic images rendered by graphics engines are a promising source for...

3 Dawei Yang, et al. ∙

research

∙ 06/10/2019

Identifying Visible Actions in Lifestyle Vlogs

We consider the task of identifying human actions visible in online vide...

1 Oana Ignat, et al. ∙

research

∙ 05/21/2019

Learning to Prove Theorems via Interacting with Proof Assistants

Humans prove theorems by relying on substantial high-level reasoning and...

32 Kaiyu Yang, et al. ∙

research

∙ 04/18/2019

CornerNet-Lite: Efficient Keypoint Based Object Detection

Keypoint-based methods are a relatively new paradigm in object detection...

20 Hei Law, et al. ∙

research

∙ 12/19/2018

D3D: Distilled 3D Networks for Video Action Recognition

State-of-the-art methods for video action recognition commonly use an en...

10 Jonathan C. Stroud, et al. ∙

research

∙ 12/11/2018

DeepV2D: Video to Depth with Differentiable Structure from Motion

We propose DeepV2D, an end-to-end differentiable deep learning architect...

18 Zachary Teed, et al. ∙

research

∙ 10/11/2018

Realistic Adversarial Examples in 3D Meshes

Highly expressive models such as deep neural networks (DNNs) have been w...

0 Dawei Yang, et al. ∙

research

∙ 09/24/2018

Speaker Naming in Movies

We propose a new model for speaker naming in movies that leverages visua...

2 Mahmoud Azab, et al. ∙

research

∙ 08/07/2018

Rethinking Numerical Representations for Deep Neural Networks

With ever-increasing computational demand for deep learning, it is criti...

10 Parker Hill, et al. ∙

research

∙ 08/03/2018

CornerNet: Detecting Objects as Paired Keypoints

We propose CornerNet, a new approach to object detection where we detect...

6 Hei Law, et al. ∙

research

∙ 06/25/2018

Learning Single-Image Depth from Videos using Quality Assessment Networks

Although significant progress has been made in recent years, depth estim...

2 Weifeng Chen, et al. ∙

research

∙ 05/25/2018

Think Visually: Question Answering through Virtual Imagery

In this paper, we study the problem of geometric reasoning in the contex...

0 Ankit Goyal, et al. ∙

research

∙ 04/23/2018

Decorrelated Batch Normalization

Batch Normalization (BN) is capable of accelerating the training of deep...

0 Lei Huang, et al. ∙

research

∙ 04/20/2018

Rethinking the Faster R-CNN Architecture for Temporal Action Localization

We propose TAL-Net, an improved approach to temporal action localization...

0 Yu-Wei Chao, et al. ∙

research

∙ 12/08/2017

Shape from Shading through Shape Evolution

In this paper, we address the shape-from-shading problem by training dee...

0 Dawei Yang, et al. ∙

research

∙ 09/28/2017

Premise Selection for Theorem Proving by Deep Graph Embedding

We propose a deep learning-based approach to the problem of premise sele...

0 Mingzhe Wang, et al. ∙

Jia Deng

Featured Co-authors