Google at ICCV 2023 – Google Research Blog

Google is proud to be a Platinum Sponsor of the International Conference on Computer Vision (ICCV 2023), a premier annual conference, which is being held this week in Paris, France. As a leader in computer vision research, Google has a strong presence at this year’s conference with 60 accepted papers and active involvement in 27 workshops and tutorials. Google is also proud to be a Platinum Sponsor for the LatinX in CV workshop. We look forward to sharing some of our extensive computer vision research and expanding our partnership with the broader research community.

Attending ICCV 2023? We hope you’ll visit the Google booth to chat with researchers who are actively pursuing the latest innovations in computer vision, and check out some of the scheduled booth activities (e.g., demos and Q&A sessions listed below). Visit the @GoogleAI Twitter account to find out more about the Google booth activities at ICCV 2023.

Take a look below to learn more about the Google research being presented at ICCV 2023 (Google affiliations in bold).

Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF SensorXinyang Liu, Yijin Li, Yanbin Teng, Hujun Bao, Guofeng Zhang, Yinda Zhang, Zhaopeng Cui

ITI-GEN: Inclusive Text-to-Image GenerationCheng Zhang, Xuanbai Chen, Siqi Chai, Chen Henry Wu, Dmitry Lagun, Thabo Beeler, Fernando De la Torre

ASIC: Aligning Sparse in-the-wild Image CollectionsKamal Gupta, Varun Jampani, Carlos Esteves, Abhinav Shrivastava, Ameesh Makadia, Noah Snavely, Abhishek Kar

VQ3D: Learning a 3D-Aware Generative Model on ImageNetKyle Sargent, Jing Yu Koh, Han Zhang, Huiwen Chang, Charles Herrmann, Pratul Srinivasan, Jiajun Wu, Deqing Sun

Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia EntitiesHexiang Hu, Yi Luan, Yang Chen*, Urvashi Khandelwal, Mandar Joshi, Kenton Lee, Kristina Toutanova, Ming-Wei Chang

Sigmoid Loss for Language Image Pre-trainingXiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer

Tracking Everything Everywhere All at OnceQianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, Noah Snavely

Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, Peter Hedman

Delta Denoising ScoreAmir Hertz*, Kfir Aberman, Daniel Cohen-Or*

DreamBooth3D: Subject-Driven Text-to-3D GenerationAmit Raj, Srinivas Kaza, Ben Poole, Michael Niemeyer, Nataniel Ruiz, Ben Mildenhall, Shiran Zada, Kfir Aberman, Michael Rubinstein, Jonathan Barron, Yuanzhen Li, Varun Jampani

Encyclopedic VQA: Visual Questions about Detailed Properties of Fine-grained CategoriesThomas Mensink, Jasper Uijlings, Lluis Castrejon, Arushi Goel*, Felipe Cadar*, Howard Zhou, Fei Sha, André Araujo, Vittorio Ferrari

GECCO: Geometrically-Conditioned Point Diffusion ModelsMichał J. Tyszkiewicz, Pascal Fua, Eduard Trulls

Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video RecognitionQitong Wang, Long Zhao, Liangzhe Yuan, Ting Liu, Xi Peng

Neural Microfacet Fields for Inverse RenderingAlexander Mai, Dor Verbin, Falko Kuester, Sara Fridovich-Keil

Rosetta Neurons: Mining the Common Units in a Model ZooAmil Dravid, Yossi Gandelsman, Alexei A. Efros, Assaf Shocher

Teaching CLIP to Count to TenRoni Paiss*, Ariel Ephrat, Omer Tov, Shiran Zada, Inbar Mosseri, Michal Irani, Tali Dekel

Vox-E: Text-guided Voxel Editing of 3D ObjectsEtai Sella, Gal Fiebelman, Peter Hedman, Hadar Averbuch-Elor

CC3D: Layout-Conditioned Generation of Compositional 3D ScenesSherwin Bahmani, Jeong Joon Park, Despoina Paschalidou, Xingguang Yan, Gordon Wetzstein, Leonidas Guibas, Andrea Tagliasacchi

Delving into Motion-Aware Matching for Monocular 3D Object TrackingKuan-Chih Huang, Ming-Hsuan Yang, Yi-Hsuan Tsai

Generative Multiplane Neural Radiance for 3D-Aware Image GenerationAmandeep Kumar, Ankan Kumar Bhunia, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan

M2T: Masking Transformers Twice for Faster DecodingFabian Mentzer, Eirikur Agustsson, Michael Tschannen

MULLER: Multilayer Laplacian Resizer for VisionZhengzhong Tu, Peyman Milanfar, Hossein Talebi

SVDiff: Compact Parameter Space for Diffusion Fine-TuningLigong Han*, Yinxiao Li, Han Zhang, Peyman Milanfar, Dimitris Metaxas, Feng Yang

Towards Authentic Face Restoration with Iterative Diffusion Models and BeyondYang Zhao, Tingbo Hou, Yu-Chuan Su, Xuhui Jia, Yandong Li, Matthias Grundmann

Unified Visual Relationship Detection with Vision and Language ModelsLong Zhao, Liangzhe Yuan, Boqing Gong, Yin Cui, Florian Schroff, Ming-Hsuan Yang, Hartwig Adam, Ting Liu

3D Motion Magnification: Visualizing Subtle Motions from Time-Varying Radiance FieldsBrandon Y. Feng, Hadi Alzayer, Michael Rubinstein, William T. Freeman, Jia-Bin Huang

Global Features are All You Need for Image Retrieval and RerankingShihao Shao, Kaifeng Chen, Arjun Karpur, Qinghua Cui, André Araujo, Bingyi Cao

Introducing Language Guidance in Prompt-Based Continual LearningMuhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal

Multiscale Structure Guided Diffusion for Image DeblurringMengwei Ren*, Mauricio Delbracio, Hossein Talebi, Guido Gerig, Peyman Milanfar

Robust Monocular Depth Estimation under Challenging ConditionsStefano Gasperini, Nils Morbitzer, HyunJun Jung, Nassir Navab, Federico Tombari

Score-Based Diffusion Models as Principled Priors for Inverse ImagingBerthy T. Feng*, Jamie Smith, Michael Rubinstein, Huiwen Chang, Katherine L. Bouman, William T. Freeman

Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image RepresentationsNikolaos-Antonios Ypsilantis, Kaifeng Chen, Bingyi Cao, Mario Lipovsky, Pelin Dogan-Schonberger, Grzegorz Makosa, Boris Bluntschli, Mojtaba Seyedhosseini, Ondrej Chum, André Araujo

U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point CloudsYan Di, Chenyangguang Zhang, Ruida Zhang, Fabian Manhardt, Yongzhi Su, Jason Rambach, Didier Stricker, Xiangyang Ji, Federico Tombari

AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose ControlRuixiang Jiang, Can Wang, Jingbo Zhang, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

Learning Versatile 3D Shape Generation with Improved AR ModelsSimian Luo, Xuelin Qian, Yanwei Fu, Yinda Zhang, Ying Tai, Zhenyu Zhang, Chengjie Wang, Xiangyang Xue

Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse ViewsWentian Qu, Zhaopeng Cui, Yinda Zhang, Chenyu Meng, Cuixia Ma, Xiaoming Deng, Hongan Wang

PreSTU: Pre-Training for Scene-Text UnderstandingJihyung Kil*, Soravit Changpinyo, Xi Chen, Hexiang Hu, Sebastian Goodman, Wei-Lun Chao, Radu Soricut

Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable ObjectsBaowen Zhang, Jiahe Li, Xiaoming Deng, Yinda Zhang, Cuixia Ma, Hongan Wang

Self-regulating Prompts: Foundational Model Adaptation without ForgettingMuhammad Uzair Khattak, Syed Talal Wasi, Muzammal Nasee, Salman Kha, Ming-Hsuan Yan, Fahad Shahbaz Khan

Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color ImagesTze Ho Elden Tse*, Franziska Mueller, Zhengyang Shen, Danhang Tang, Thabo Beeler, Mingsong Dou, Yinda Zhang, Sasa Petrovic, Hyung Jin Chang, Jonathan Taylor, Bardia Doosti

Synthesizing Diverse Human Motions in 3D Indoor ScenesKaifeng Zhao, Yan Zhang, Shaofei Wang, Thabo Beeler, Siyu Tang

Tracking by 3D Model Estimation of Unknown Objects in VideosDenys Rozumnyi, Jiri Matas, Marc Pollefeys, Vittorio Ferrari, Martin R. Oswald

UnLoc: A Unified Framework for Video Localization TasksShen Yan, Xuehan Xiong, Arsha Nagrani, Anurag Arnab, Zhonghao Wang*, Weina Ge, David Ross, Cordelia Schmid

Verbs in Action: Improving Verb Understanding in Video-language ModelsLiliane Momeni, Mathilde Caron, Arsha Nagrani, Andrew Zisserman, Cordelia Schmid

VLSlice: Interactive Vision-and-Language Slice DiscoveryEric Slyman, Minsuk Kahng, Stefan Lee

Yes, we CANN: Constrained Approximate Nearest Neighbors for Local Feature-Based Visual LocalizationDror Aiger, André Araujo, Simon Lynen

Audiovisual Masked AutoencodersMariana-Iuliana Georgescu*, Eduardo Fonseca, Radu Tudor Ionescu, Mario Lucic, Cordelia Schmid, Anurag Arnab

CLR: Channel-wise Lightweight Reprogramming for Continual LearningYunhao Ge, Yuecheng Li, Shuo Ni, Jiaping Zhao, Ming-Hsuan Yang, Laurent Itti

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFsZezhou Cheng*, Carlos Esteves, Varun Jampani, Abhishek Kar, Subhransu Maji, Ameesh Makadia

Multiscale Representation for Real-Time Anti-Aliasing Neural RenderingDongting Hu, Zhenkai Zhang, Tingbo Hou, Tongliang Liu, Huan Fu, Mingming Gong

Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFsFrederik Warburg, Ethan Weber, Matthew Tancik, Aleksander Holynski, Angjoo Kanazawa

Segmenting Known Objects and Unseen Unknowns without Prior KnowledgeStefano Gasperini, Alvaro Marcos-Ramiro, Michael Schmidt, Nassir Navab, Benjamin Busam, Federico Tombari 

SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object DetectionYichen Xie, Chenfeng Xu, Marie-Julie Rakotosaona, Patrick Rim, Federico Tombari, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan

SwiftFormer: Efficient Additive Attention for Transformer-Based Real-time Mobile Vision ApplicationsAbdelrahman Shaker, Muhammad Maa, Hanoona Rashee, Salman Kha, Ming-Hsuan Yan, Fahad Shahbaz Kha

Agile Modeling: From Concept to Classifier in MinutesOtilia Stretcu, Edward Vendrow, Kenji Hata, Krishnamurthy Viswanathan, Vittorio Ferrari, Sasan Tavakkol, Wenlei Zhou, Aditya Avinash, Enming Luo, Neil Gordon Alldrin, MohammadHossein Bateni, Gabriel Berger, Andrew Bunner, Chun-Ta Lu, Javier A Rey, Giulia DeSalvo, Ranjay Krishna, Ariel Fuxman

CAD-Estate: Large-Scale CAD Model Annotation in RGB VideosKevis-Kokitsi Maninis, Stefan Popov, Matthias Niessner, Vittorio Ferrari

Counting Crowds in Bad WeatherZhi-Kai Huang, Wei-Ting Chen, Yuan-Chun Chiang, Sy-Yen Kuo, Ming-Hsuan Yang

DreamPose: Fashion Video Synthesis with Stable DiffusionJohanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher-Shlizerman

InfiniCity: Infinite-Scale City SynthesisChieh Hubert Lin, Hsin-Ying Lee, Willi Menapace, Menglei Chai, Aliaksandr Siarohin, Ming-Hsuan Yang, Sergey Tulyakov

SAMPLING: Scene-Adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single ImageXiaoyu Zhou, Zhiwei Lin, Xiaojun Shan, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang

The post Google at ICCV 2023 – Google Research Blog appeared first on AIPressRoom.