Google AI Weblog: Google at ICCV 2021

0
24


The Worldwide Convention on Pc Imaginative and prescient 2021 (ICCV 2021), one of many world’s premier conferences on pc imaginative and prescient, begins this week. A Champion Sponsor and chief in pc imaginative and prescient analysis, Google can have a robust presence at ICCV 2021 with greater than 50 analysis displays and involvement within the group of quite a lot of workshops and tutorials.

If you’re attending ICCV this 12 months, we hope you’ll try the work of our researchers who’re actively pursuing the most recent improvements in pc imaginative and prescient. Study extra about our analysis being introduced within the listing under (Google affilitation in daring).

Organizing Committee
Variety and Inclusion Chair: Negar Rostamzadeh
Space Chairs: Andrea Tagliasacchi, Boqing Gong, Ce Liu, Dilip Krishnan, Jordi Pont-Tuset, Michael Rubinstein, Michael S. Ryoo, Negar Rostamzadeh, Noah Snavely, Rodrigo Benenson, Tsung-Yi Lin, Vittorio Ferrari

Publications
MosaicOS: A Easy and Efficient Use of Object-Centric Photographs for Lengthy-Tailed Object Detection
Cheng Zhang, Tai-Yu Pan, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao

Studying to Resize Photographs for Pc Imaginative and prescient Duties
Hossein Talebi, Peyman Milanfar

Joint Illustration Studying and Novel Class Discovery on Single- and Multi-Modal Information
Xuhui Jia, Kai Han, Yukun Zhu, Bradley Inexperienced

Explaining in Fashion: Coaching a GAN to Clarify a Classifier in StyleSpace
Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald, Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola, Amir Globerson, Michal Irani, Inbar Mosseri

Studying Quick Pattern Re-weighting with out Reward Information
Zizhao Zhang, Tomas Pfister

Contrastive Multimodal Fusion with TupleInfoNCE
Yunze Liu, Qingnan Fan, Shanghang Zhang, Hao Dong, Thomas Funkhouser, Li Yi

Studying Temporal Dynamics from Cycles in Narrated Video
Dave Epstein*, Jiajun Wu, Cordelia Schmid, Chen Solar

Patch Craft: Video Denoising by Deep Modeling and Patch Matching
Gregory Vaksman, Michael Elad, Peyman Milanfar

Tips on how to Prepare Neural Networks for Flare Removing
Yicheng Wu*, Qiurui He, Tianfan Xue, Rahul Garg, Jiawen Chen, Ashok Veeraraghavan, Jonathan T. Barron

Studying to Cut back Defocus Blur by Realistically Modeling Twin-Pixel Information
Abdullah Abuolaim*, Mauricio Delbracio, Damien Kelly, Michael S. Brown, Peyman Milanfar

Hybrid Neural Fusion for Full-Body Video Stabilization
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang

A Darkish Flash Regular Digital camera
Zhihao Xia*, Jason Lawrence, Supreeth Achar

Environment friendly Giant Scale Inlier Voting for Geometric Imaginative and prescient Issues
Dror Aiger, Simon Lynen, Jan Hosang, Bernhard Zeisl

Huge Self-Supervised Fashions Advance Medical Picture Classification
Shekoofeh Azizi, Basil Mustafa, Fiona Ryan*, Zachary Beaver, Jan Freyberg, Jonathan Deaton, Aaron Loh, Alan Karthikesalingam, Simon Kornblith, Ting Chen, Vivek Natarajan, Mohammad Norouzi

Physics-Enhanced Machine Studying for Digital Fluorescence Microscopy
Colin L. Cooke, Fanjie Kong, Amey Chaware, Kevin C. Zhou, Kanghyun Kim, Rong Xu, D. Michael Ando, Samuel J. Yang, Pavan Chandra Konda, Roarke Horstmeyer

Retrieve in Fashion: Unsupervised Facial Characteristic Switch and Retrieval
Min Jin Chong, Wen-Sheng Chu, Abhishek Kumar, David Forsyth

Deep Survival Evaluation with Longitudinal X-Rays for COVID-19
Michelle Shu, Richard Robust Bowen, Charles Herrmann, Gengmo Qi, Michele Santacatterina, Ramin Zabih

MUSIQ: Multi-Scale Picture High quality Transformer
Junjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar, Feng Yang

imGHUM: Implicit Generative Fashions of 3D Human Form and Articulated Pose
Thiemo Alldieck, Hongyi Xu, Cristian Sminchisescu

Deep Hybrid Self-Prior for Full 3D Mesh Era
Xingkui Wei, Zhengqing Chen, Yanwei Fu, Zhaopeng Cui, Yinda Zhang

Differentiable Floor Rendering by way of Non-Differentiable Sampling
Forrester Cole, Kyle Genova, Avneesh Sud, Daniel Vlasic, Zhoutong Zhang

A Lazy Strategy to Lengthy-Horizon Gradient-Primarily based Meta-Studying
Muhammad Abdullah Jamal, Liqiang Wang, Boqing Gong

ViViT: A Video Imaginative and prescient Transformer
Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Solar, Mario Lučić, Cordelia Schmid

The Stunning Influence of Masks-Head Structure on Novel Class Segmentation (see the weblog submit)
Vighnesh Birodkar, Zhichao Lu, Siyang Li, Vivek Rathod, Jonathan Huang

Generalize Then Adapt: Supply-Free Area Adaptive Semantic Segmentation
Jogendra Nath Kundu, Akshay Kulkarni, Amit Singh, Varun Jampani, R. Venkatesh Babu

Unified Graph Structured Fashions for Video Understanding
Anurag Arnab, Chen Solar, Cordelia Schmid

The Many Faces of Robustness: A Vital Evaluation of Out-of-Distribution Generalization
Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Daybreak Music, Jacob Steinhardt, Justin Gilmer

Studying Uncommon Class Classifiers on a Tight Labeling Price range
Ravi Teja Mullapudi, Fait Poms, William R. Mark, Deva Ramanan, Kayvon Fatahalian

Composable Augmentation Encoding for Video Illustration Studying
Chen Solar, Arsha Nagrani, Yonglong Tian, Cordelia Schmid

Multi-Activity Self-Coaching for Studying Basic Representations
Golnaz Ghiasi, Barret Zoph, Ekin D. Cubuk, Quoc V. Le, Tsung-Yi Lin

With a Little Assist From My Associates: Nearest-Neighbor Contrastive Studying of Visible Representations
Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

Understanding Robustness of Transformers for Picture Classification
Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit

Influence of Aliasing on Generalization in Deep Convolutional Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Rob Romijnders, Nicolas Le Roux, Ross Goroshin

von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Studying
Tyler R. Scott*, Andrew C. Gallagher, Michael C. Mozer

Contrastive Studying for Label Environment friendly Semantic Segmentation
Xiangyun Zhao*, Raviteja Vemulapalli, Philip Andrew Mansfield, Boqing Gong, Bradley Inexperienced, Lior Shapira, Ying Wu

Interacting Two-Hand 3D Pose and Form Reconstruction from Single Coloration Picture
Baowen Zhang, Yangang Wang, Xiaoming Deng, Yinda Zhang, Ping Tan, Cuixia Ma, Hongan Wang

Telling the What Whereas Pointing to the The place: Multimodal Queries for Picture Retrieval
Soravit Changpinyo, Jordi Pont-Tuset, Vittorio Ferrari, Radu Soricut

SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation
Yan Di, Fabian Manhardt, Gu Wang, Xiangyang Ji, Nassir Navab, Federico Tombari

Patch2CAD: Patchwise Embedding Studying for In-the-Wild Form Retrieval from a Single Picture
Weicheng Kuo, Anelia Angelova, Tsung-Yi Lin, Angela Dai

NeRD: Neural Reflectance Decomposition From Picture Collections
Mark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron, Ce Liu, Hendrik P.A. Lensch

THUNDR: Transformer-Primarily based 3D Human Reconstruction with Markers
Mihai Zanfir, Andrei Zanfir, Eduard Gabriel Bazavan, William T. Freeman, Rahul Sukthankar, Cristian Sminchisescu

Discovering 3D Components from Picture Collections
Chun-Han Yao, Wei-Chih Hung, Varun Jampani, Ming-Hsuan Yang

Multiresolution Deep Implicit Capabilities for 3D Form Illustration
Zhang Chen*, Yinda Zhang, Kyle Genova, Sean Fanello, Sofien Bouaziz, Christian Hane, Ruofei Du, Cem Keskin, Thomas Funkhouser, Danhang Tang

AI Choreographer: Music Conditioned 3D Dance Era With AIST++ (see the weblog submit)
Ruilong Li*, Shan Yang, David A. Ross, Angjoo Kanazawa

Studying Object-Compositional Neural Radiance Subject for Editable Scene Rendering
Bangbang Yang, Han Zhou, Yinda Zhang, Hujun Bao, Yinghao Xu, Guofeng Zhang, Yijin Li, Zhaopeng Cui

VariTex: Variational Neural Face Textures
Marcel C. Buhler, Abhimitra Meka, Gengyan Li, Thabo Beeler, Otmar Hilliges

Pathdreamer: A World Mannequin for Indoor Navigation (see the weblog submit)
Jing Yu Koh, Honglak Lee, Yinfei Yang, Jason Baldridge, Peter Anderson

4D-Internet for Realized Multi-Modal Alignment
AJ Piergiovanni, Vincent Casser, Michael S. Ryoo, Anelia Angelova

Episodic Transformer for Imaginative and prescient-and-Language Navigation
Alexander Pashevich*, Cordelia Schmid, Chen Solar

Graph-to-3D: Finish-to-Finish Era and Manipulation of 3D Scenes Utilizing Scene Graphs
Helisa Dhamo, Fabian Manhardt, Nassir Navab, Federico Tombari

Unconditional Scene Graph Era
Sarthak Garg, Helisa Dhamo, Azade Farshad, Sabrina Musatian, Nassir Navab, Federico Tombari

Panoptic Narrative Grounding
Cristina González, Nicolás Ayobi, Isabela Hernández, José Hernández, Jordi Pont-Tuset, Pablo Arbeláez

Cross-Digital camera Convolutional Coloration Fidelity
Mahmoud Afifi*, Jonathan T. Barron, Chloe LeGendre, Yun-Ta Tsai, Francois Bleibel

Defocus Map Estimation and Deblurring from a Single Twin-Pixel Picture
Shumian Xin*, Neal Wadhwa, Tianfan Xue, Jonathan T. Barron, Pratul P. Srinivasan, Jiawen Chen, Ioannis Gkioulekas, Rahul Garg

COMISR: Compression-Knowledgeable Video Tremendous-Decision
Yinxiao Li, Pengchong Jin, Feng Yang, Ce Liu, Ming-Hsuan Yang, Peyman Milanfar

Mip-NeRF: A Multiscale Illustration for Anti-Aliasing Neural Radiance Fields
Jonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, Pratul P. Srinivasan

Nerfies: Deformable Neural Radiance Fields
Keunhong Park*, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Steven M. Seitz, Ricardo Martin-Brualla

Baking Neural Radiance Fields for Actual-Time View Synthesis
Peter Hedman, Pratul P. Srinivasan, Ben Mildenhall, Jonathan T. Barron, Paul Debevec

Stacked Homography Transformations for Multi-View Pedestrian Detection
Liangchen Music, Jialian Wu, Ming Yang, Qian Zhang, Yuan Li, Junsong Yuan

COTR: Correspondence Transformer for Matching Throughout Photographs
Wei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi, Kwang Moo Yi

Giant Scale Interactive Movement Forecasting for Autonomous Driving: The Waymo Open Movement Dataset
Scott Ettinger, Shuyang Cheng, Benjamin Caine, Chenxi Liu, Cling Zhao, Sabeek Pradhan, Yuning Chai, Ben Sapp, Charles R. Qi, Yin Zhou, Zoey Yang, Aurélien Chouard, Pei Solar, Jiquan Ngiam, Vijay Vasudevan, Alexander McCauley, Jonathon Shlens, Dragomir Anguelov

Low-Shot Validation: Energetic Significance Sampling for Estimating Classifier Efficiency on Uncommon Classes
Fait Poms, Vishnu Sarukkai, Ravi Teja Mullapudi, Nimit S. Sohoni, William R. Mark, Deva Ramanan, Kayvon Fatahalian

Vector Neurons: A Basic Framework for SO(3)-Equivariant Networks
Congyue Deng, Or Litany, Yueqi Duan, Adrien Poulenard, Andrea Tagliasacchi, Leonidas J. Guibas

SLIDE: Single Picture 3D Pictures with Smooth Layering and Depth-Conscious Inpainting
Varun Jampani, Huiwen Chang, Kyle Sargent, Abhishek Kar, Richard Tucker, Michael Krainin,

Dominik Kaeser, William T. Freeman, David Salesin, Brian Curless, Ce Liu

DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-Primarily based Optimization
Cheng Zhang, Zhaopeng Cui, Cai Chen, Shuaicheng Liu, Bing Zeng, Hujun Bao, Yinda Zhang

Infinite Nature: Perpetual View Era of Pure Scenes from a Single Picture
Andrew Liu, Richard Tucker, Varun Jampani, Ameesh Makadia, Noah Snavely, Angjoo Kanazawa

Workshops (solely Google affiliations are famous)
Visible Inductive Priors for Information-Environment friendly Deep Studying Workshop
Audio system: Ekin Dogus Cubuk, Chelsea Finn

Occasion-Stage Recognition Workshop
Organizers: Andre Araujo, Cam Askew, Bingyi Cao, Jack Sim, Tobias Weyand

Unsup3D: Unsupervised 3D Studying within the Wild
Audio system: Adel Ahmadyan, Noah Snavely, Tali Dekel

Embedded and Actual-World Pc Imaginative and prescient in Autonomous Driving (ERCVAD 2021)
Audio system: Mingxing Tan

Adversarial Robustness within the Actual World
Audio system: Nicholas Carlini

Neural Architectures: Previous, Current and Future
Audio system: Been Kim, Hanxiao Liu

Organizers: Azade Nazi, Mingxing Tan, Quoc V. Le

Computational Challenges in Digital Pathology
Organizers: Craig Mermel, Po-Hsuan Cameron Chen

Interactive Labeling and Information Augmentation for Imaginative and prescient
Audio system: Vittorio Ferrari

Map-Primarily based Localization for Autonomous Driving
Audio system: Simon Lynen

DeeperAction: Problem and Workshop on Localized and Detailed Understanding of Human Actions in Movies
Audio system: Chen Solar

Advisors: Rahul Sukthankar

Differentiable 3D Imaginative and prescient and Graphics
Audio system: Angjoo Kanazawa

Deep Multi-Activity Studying in Pc Imaginative and prescient
Audio system: Chelsea Finn

Pc Imaginative and prescient for AR/VR
Audio system: Matthias Grundmann, Ira Kemelmacher-Shlizerman

GigaVision: When Gigapixel Videography Meets Pc Imaginative and prescient
Organizers: Feng Yang

Human Interplay for Robotic Navigation
Audio system: Peter Anderson

Advances in Picture Manipulation Workshop and Challenges
Organizers: Ming-Hsuan Yang

Extra Exploration, Much less Exploitation (MELEX)
Audio system: Angjoo Kanazawa

Structural and Compositional Studying on 3D Information
Audio system: Thomas Funkhouser, Kyle Genova

Organizers: Fei Xia

Simulation Expertise for Embodied AI
Organizers: Li Yi

Video Scene Parsing within the Wild Problem Workshop
Audio system: Liang-Chieh (Jay) Chen

Structured Representations for Video Understanding
Organizers: Cordelia Schmid

Closing the Loop Between Imaginative and prescient and Language
Audio system: Cordelia Schmid

Segmenting and Monitoring Each Level and Pixel: sixth Workshop on Benchmarking Multi-Goal Monitoring
Organizers: Jun Xie, Liang-Chieh Chen

AI for Inventive Video Enhancing and Understanding
Audio system: Angjoo Kanazawa, Irfan Essa

BEHAVIOR: Benchmark for On a regular basis Family Actions in Digital, Interactive, and Ecological Environments
Audio system: Chelsea Finn

Organizers: Fei Xia

Pc Imaginative and prescient for Automated Medical Analysis
Organizers: Maithra Raghu

Pc Imaginative and prescient for the Manufacturing unit Flooring
Audio system: Cordelia Schmid

Tutorials (solely Google affiliations are famous)
In the direction of Sturdy, Reliable, and Explainable Pc Imaginative and prescient
Audio system: Sara Hooker

Multi-Modality Studying from Movies and Past
Organizers: Arsha Nagrani

Tutorial on Giant Scale Holistic Video Understanding
Organizers: David Ross

Environment friendly Video Understanding: State of the Artwork, Challenges, and Alternatives
Organizers: Arsha Nagrani

* Signifies work accomplished whereas at Google

LEAVE A REPLY

Please enter your comment!
Please enter your name here