Adobe at ECCV 2022 

October 28, 2022

Tags: Conferences

This ECCV paper introduces a novel method for diverse, sketch-driven image synthesis with fine-grained control over structure and appearance.

At this year’s European Conference on Computer Vision (ECCV 2022), held from October 23 through October 27, 2022, Adobe has co-authored a total of 43 main conference papers, including 4 oral papers and 39 poster papers, plus 6 workshop papers.   

Adobe authors have also contributed to the conference in many other ways, including co-organizing several workshops, area chairing, and reviewing papers.  

Nearly all these papers are the result of research internships or other collaborations with university students and faculty. Please check out Adobe Research’s careers page to learn more about internships and full-time career opportunities.   

Here are Adobe’s contributions to ECCV 2022. 

Oral papers 

OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses 
Robik Shrestha, Kushal Kafle, Christopher Kanan 

Perceptual Artifacts Localization for Inpainting 
Lingzhi Zhang, Yuqian Zhou, Connelly Barnes, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi, Jianbo Shi 

Physically-Based Editing of Indoor Scene Lighting from a Single Image 
Zhengqin Li, Jia Shi, Sai Bi, Rui Zhu, Kalyan Sunkavalli, Milos Hasan, Zexiang Xu, Ravi Ramamoorthi, Manmohan Chandraker 

Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition 
Xudong Xie, Ling Fu, Zhifei Zhang, Zhaowen Wang, Xiang Bai 

Poster papers 

3D-FM GAN: Towards 3D-Controllable Face Manipulation 
Yuchen Liu, Zhixin Shu, Yijun Li, Zhe Lin, Richard Zhang, Sun-Yuan Kung 

A Repulsive Force Unit for Garment Collision Handling in Neural Networks 
Qingyang Tan, Yi Zhou, Tuanfeng Wang, Duygu Ceylan, Xin Sun, Dinesh Manocha 

Any-resolution Training for High-resolution Image Synthesis 
Lucy Chai, Michaël Gharbi, Eli Shechtman, Phillip Isola, Richard Zhang 

ARF: Artistic Radiance fields 
Kai Zhang, Nicholas Kolkin, Sai Bi, Fujun Luan, Zexiang Xu, Eli Shechtman, Noah Snavely 

BlobGAN: Spatially Disentangled Scene Representations 
Dave Epstein, Taesung Park, Richard Zhang, Eli Shechtman, Alexei Efros 

Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection 
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee 

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation 
Lu Qi, Jason Kuen, Zhe Lin, Jiuxiang Gu, Fengyun Rao, Dian Li, Weidong Guo, Zhen Wen, Ming-Hsuan Yang, Jiaya Jia 

ChunkyGAN: Real Image Inversion via Segments 
Adéla Šubrtová, David Futschik, Jan Čech, Michal Lukáč, Eli Shechtman, Daniel Sýkora 

CoGS: Controllable Generation and Search from Sketch and Style 
Cusuh Ham, Gemma Canet Tarrés, Tu Bui, James Hays, Zhe Lin, John Collomosse 

Contrastive Learning for Diverse Disentangled Foreground Generation 
Yuheng Li, Yijun Li, Jingwan Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh 

Controllable Shadow Generation Using Pixel Heigh Maps 
Yichen Sheng, Yifan Liu, Jianming Zhang, Wei Yin, A. Cengiz Oztireli, He Zhang, Zhe Lin, Eli Shechtman, Bedrich Benes 

Deep 360° Optical Flow Estimation by Multi-Projection Fusion 
Yiheng Li, Connelly Barnes, Kun Huang, Fang-Lue Zhang 

Distilling the Undistillable: Learning from a Nasty Teacher 
Surgan Jandial, Yash Khasbage, Arghya Pal, Vineeth Balasubramanian, Balaji Krishnamurthy 

Error Compensation Framework for Flow-Guided Video Inpainting 
Jaeyeon Kang, Seoung Wug Oh, Seon Joo Kim 

GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing 
Sijie Zhu, Zhe Lin, Scott Cohen, Jason Kuen, Zhifei Zhang, Chen Chen 

Image Inpainting with Cascaded Modulation GAN and Object-Aware Training 
Haitian Zheng, Zhe Lin, Jingwan Lu, Scott Cohen, Eli Shechtman, Connelly Barnes, Jianming Zhang, Ning Xu, Sohrab Amirghodsi, Jiebo Luo 

Improving Closed and Open-Vocabulary Attribute Prediction using Transformers 
Khoi Pham, Kushal Kafle, Zhe Lin, Zhihong Ding, Scott Cohen, Quan Hung Tran, Abhinav Shrivastava 

Improving the Reliability for Confidence Estimation 
Haoxuan Qu, Yanchao Li, Lin Geng Foo, Jason Kuen, Jiuxiang Gu, Jun Liu 

Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation 
Connelly Barnes, Lingzhi Zhang, Jianbo Shi, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi, Kevin Wampler 

Intelli-Paint: Towards Developing More Human-Intelligible Painting Agents 
Jaskirat Singh, Cameron Smith, Jose Echevarria, Liang Zheng 

Learning an Isometric Surface Parameterization for Texture Unwrapping 
Sagnik Das, Ke Ma, Zhixin Shu, Dimitris Samaras 

Learning Visibility for Robust Dense Human Body Estimation 
Chun-Han Yao, Jimei Yang, Duygu Ceylan, Yi Zhou, Yang Zhou, Ming-Hsuan Yang 

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation 
LI XU, Haoxuan Qu, Jason Kuen, Jiuxiang Gu, Jun Liu 

MovieCuts: A New Dataset and Benchmark forCut Type Recognition 
Alejandro Pardo, Fabian Caba, Juan C Leon, Ali K Thabet, Bernard Ghanem 

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects 
Juewen Peng, Jianming Zhang, Xianrui Luo, Hao Lu, Ke Xian, Zhiguo Cao 

One-Trimap Video Matting 
Hongje Seong, Seoung Wug Oh, Brian Price, Euntai Kim, Joon-Young Lee 

Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing 
Jaskirat Singh, Liang Zheng, Cameron Y Smith, Jose Echevarria 

PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation 
Bo Sun, Vladimir Kim, Qixing Huang, Noam Aigerman, Siddhartha Chaudhuri 

RepMix: Representation Mixing for Robust Attribution of Synthesized Images 
Tu Bui, Ning Yu, John Collomosse 

Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency 
Tom Monnier, Matthew Fisher, Alexei A Efros, Mathieu Aubry 

Skeleton-free Pose Transfer for Stylized 3D Characters 
Zhouyingcheng Liao, Jimei Yang, Jun Saito, Gerard Pons-Moll, Yang Zhou 

Spotting Temporally Precise, Fine-Grained Events in Video 
James Hong, Haotian Zhang, Michaël Gharbi, Matthew Fisher, Kayvon Fatahalian 

StyleBabel: Artistic Style Tagging and Captioning 
Dan Ruta, Andrew Gilbert, Pranav Aggarwal, Naveen Marri, Ajinkya Kale, Jo Briggs, Chris Speed, Hailin Jin, Baldo Faieta, Alex Filipkowski, Zhe Lin, John Collomosse 

TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information 
Suraj Kothawade, Saikat Ghosh, Sumit Shekhar, Yu Xiang, Rishabh Iyer 

TensoRF: Tensorial Radiance Fields 
Anpei Chen, Zexiang Xu, Andreas Geiger, Jingyi Yu, Hao Su 

The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing 
Dawit Mureja Argaw, Fabian Caba, Joon-Young Lee, Markus Woodson, In So Kweon 

The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts 
Kai Wang, Paul Guerrero, Vladimir Kim, Siddhartha Chaudhuri, Minhyuk Sung, Daniel Ritchie 

Tracking by Associating Clips 
Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee 

Video Activity Localisation with Uncertainties in Temporal Boundary 
Jiabo Huang, Hailin Jin, Shaogang Gong, Yang Liu 

Workshop papers 

Discovering and Mitigating Biases in CLIP-based Text-to-Image Generation 
Md Mehrab Tanjim, Krishna Kumar Singh, Kushal Kafle, Ritwik Sinha, Garrison W. Cottrell 
Presented at the Responsible Computer Vision workshop 

End-to-end Document Recognition and Understanding with Dessurt 
Brian Davis, Bryan Morse, Chris Tensmeyer, Brian Price, Curtis Wigington, Vlad Morariu 
Presented at the Text in Everything workshop 

HyperNST: Hyper-Networks for Neural Style Transfer 
Dan Ruta, Andrew Gilbert, Saeid Motiian, Baldo Faieta, Zhe Lin, John Collomosse 
Presented at the VISART – Vision for Art workshop 

Learning Joint Surface Atlases 
Theo Deprelle, Thibault Groueix, Noam Aigerman, Vladimir Kim, Mathieu Aubry 
Presented at the Learning to Generate 3D Shapes and Scenes workshop 

Recovering Detail in 3D Shapes Using Disparity Maps 
Marissa Ramirez de Chanlatte, Matheus Gadelha, Thibault Groueix, Radomir Mech 
Presented at the Learning to Generate 3D Shapes and Scenes workshop 

Third Time’s the Charm? Image and Video Editing with StyleGAN3 
Yuval Alaluf, Or Patashnik, Zongze Wu, Asif Zamir, Eli Shechtman, Dani Lischinski, Daniel Cohen-Or 
Presented at the Advances in Image Manipulation workshop 

Workshop co-organizer 

Drawings and Abstract Imagery: Representation and Analysis (DIRA) 
Kushal Kafle, Chris Tensmeyer, Sumit Shekhar 

Sketching for Human Expressivity
Richard Zhang

Invited talk 

Keynote at the Drawings and Abstract Imagery: Representation and Analysis (DIRA) workshop 
Niloy Mitra 

Keynote at the VISART Vision for Art workshop  
John Collomosse 

Related Posts