Search Results for author: Adam W. Harley

Found 16 papers, 4 papers with code

A Simple Baseline for BEV Perception Without LiDAR

no code implementations16 Jun 2022 Adam W. Harley, Zhaoyuan Fang, Jie Li, Rares Ambrus, Katerina Fragkiadaki

Current methods use multi-view RGB data collected from cameras around the vehicle and neurally "lift" features from the perspective images to the 2D ground plane, yielding a "bird's eye view" (BEV) feature representation of the 3D space around the vehicle.

Autonomous Vehicles Data Augmentation

Particle Videos Revisited: Tracking Through Occlusions Using Point Trajectories

no code implementations8 Apr 2022 Adam W. Harley, Zhaoyuan Fang, Katerina Fragkiadaki

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.

Motion Estimation Object Tracking +1

CoCoNets: Continuous Contrastive 3D Scene Representations

1 code implementation CVPR 2021 Shamit Lal, Mihir Prabhudesai, Ishita Mediratta, Adam W. Harley, Katerina Fragkiadaki

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.

3D Object Detection Contrastive Learning +3

Move to See Better: Self-Improving Embodied Object Detection

1 code implementation30 Nov 2020 Zhaoyuan Fang, Ayush Jain, Gabriel Sarch, Adam W. Harley, Katerina Fragkiadaki

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.

object-detection Object Detection

3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations

no code implementations30 Oct 2020 Mihir Prabhudesai, Shamit Lal, Hsiao-Yu Fish Tung, Adam W. Harley, Shubhankar Potdar, Katerina Fragkiadaki

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.

3D Object Recognition Pose Estimation

Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping

no code implementations ECCV 2020 Adam W. Harley, Shrinidhi K. Lakshmikanth, Paul Schydlo, Katerina Fragkiadaki

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.

3D Object Tracking Object Tracking

Image Disentanglement and Uncooperative Re-Entanglement for High-Fidelity Image-to-Image Translation

no code implementations11 Jan 2019 Adam W. Harley, Shih-En Wei, Jason Saragih, Katerina Fragkiadaki

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.

Disentanglement Image-to-Image Translation +1

Reward Learning from Narrated Demonstrations

no code implementations CVPR 2018 Hsiao-Yu Fish Tung, Adam W. Harley, Liang-Kang Huang, Katerina Fragkiadaki

Humans effortlessly "program" one another by communicating goals and desires in natural language.

Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision

no code implementations ICCV 2017 Hsiao-Yu Fish Tung, Adam W. Harley, William Seto, Katerina Fragkiadaki

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.

3D Human Pose Estimation Image-to-Image Translation +2

Learning Dense Convolutional Embeddings for Semantic Segmentation

no code implementations13 Nov 2015 Adam W. Harley, Konstantinos G. Derpanis, Iasonas Kokkinos

That is, for any two pixels on the same object, the embeddings are trained to be similar; for any pair that straddles an object boundary, the embeddings are trained to be dissimilar.

General Classification Semantic Segmentation

Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval

no code implementations25 Feb 2015 Adam W. Harley, Alex Ufkes, Konstantinos G. Derpanis

This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs).

Document Image Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.