Search Results for author: Andrew Liu

Found 14 papers, 5 papers with code

AICOM-MP: an AI-based Monkeypox Detector for Resource-Constrained Environments

no code implementations21 Nov 2022 Tim Tianyi Yang, Tom Tianze Yang, Andrew Liu, Jie Tang, Na An, Shaoshan Liu, Xue Liu

Also, through the AICOM-MP project, we have generalized a methodology of developing health AI technologies for AMCs to allow universal access even in resource-constrained environments.

Urban Radiance Fields

no code implementations CVPR 2022 Konstantinos Rematas, Andrew Liu, Pratul P. Srinivasan, Jonathan T. Barron, Andrea Tagliasacchi, Thomas Funkhouser, Vittorio Ferrari

The goal of this work is to perform 3D reconstruction and novel view synthesis from data captured by scanning platforms commonly deployed for world mapping in urban outdoor environments (e. g., Street View).

3D Reconstruction Novel View Synthesis

Scalable Robust Federated Learning with Provable Security Guarantees

no code implementations29 Sep 2021 Andrew Liu, Jacky Y. Zhang, Nishant Kumar, Dakshita Khurana, Oluwasanmi O Koyejo

Federated averaging, the most popular aggregation approach in federated learning, is known to be vulnerable to failures and adversarial updates from clients that wish to disrupt training.

Federated Learning

Depth-supervised NeRF: Fewer Views and Faster Training for Free

1 code implementation CVPR 2022 Kangle Deng, Andrew Liu, Jun-Yan Zhu, Deva Ramanan

Crucially, SFM also produces sparse 3D points that can be used as "free" depth supervision during training: we add a loss to encourage the distribution of a ray's terminating depth matches a given 3D keypoint, incorporating depth uncertainty.

RGB-D Reconstruction

Repopulating Street Scenes

no code implementations CVPR 2021 Yifan Wang, Andrew Liu, Richard Tucker, Jiajun Wu, Brian L. Curless, Steven M. Seitz, Noah Snavely

We present a framework for automatically reconfiguring images of street scenes by populating, depopulating, or repopulating them with objects such as pedestrians or vehicles.

Autonomous Driving

Automated Backend-Aware Post-Training Quantization

no code implementations27 Mar 2021 Ziheng Jiang, Animesh Jain, Andrew Liu, Josh Fromm, Chengqian Ma, Tianqi Chen, Luis Ceze

Quantization is a key technique to reduce the resource requirement and improve the performance of neural network deployment.

Quantization

Automated Discovery of Real-Time Network Camera Data From Heterogeneous Web Pages

no code implementations23 Mar 2021 Ryan Dailey, Aniesh Chawla, Andrew Liu, Sripath Mishra, Ling Zhang, Josh Majors, Yung-Hsiang Lu, George K. Thiruvathukal

Reduction in the cost of Network Cameras along with a rise in connectivity enables entities all around the world to deploy vast arrays of camera networks.

Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image

1 code implementation ICCV 2021 Andrew Liu, Richard Tucker, Varun Jampani, Ameesh Makadia, Noah Snavely, Angjoo Kanazawa

We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image.

Image Generation Perpetual View Generation +1

Learning to Factorize and Relight a City

no code implementations ECCV 2020 Andrew Liu, Shiry Ginosar, Tinghui Zhou, Alexei A. Efros, Noah Snavely

We propose a learning-based framework for disentangling outdoor scenes into temporally-varying illumination and permanent scene factors.

Intrinsic Image Decomposition

Exploring Cellular Protein Localization Through Semantic Image Synthesis

no code implementations25 Sep 2019 Daniel Li, Qiang Ma, Andrew Liu, Justin Cheung, Dana Pe’er, Itsik Pe’er

Cell-cell interactions have an integral role in tumorigenesis as they are critical in governing immune responses.

Image Generation Management +1

Fighting Fake News: Image Splice Detection via Learned Self-Consistency

3 code implementations ECCV 2018 Minyoung Huh, Andrew Liu, Andrew Owens, Alexei A. Efros

In this paper, we propose a learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs.

Image Forensics

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