Let's create experiences that matter.
An ideal balance of academic discovery and industry impact: that’s what drives our groundbreaking work at Adobe Research.
Explore our work at CVPR and sign up to stay in touch with us for future recruiting opportunities and research collaborations.
Our Impact at CVPR
Wednesday, June 11 | Workshops
8:55AM - 9:25AM: C3DV: 3rd Workshop on Compositional 3D Vision by Vladimir (Vova) Kim | Location: Room 110B
8:55AM - 5:30PM: 1st Workshop on Humanoid Agents: HUMOTO - A 4D Dataset of Mocap Human Object Interactions by Yi Zhou | Location: Room 101D
Thursday, June 12 | Workshops
8:30AM: 3D Digital Twin: Progress, Challenges, and Future Directions by Kalyan Sunkavalli | Location: Room 102B
8:30AM: Syntagen: Inventing Data: An Industry Perspective by Nathan Carr, Yi Zhou | Location: Room 106B
9:00AM - 5:00PM: Embodied AI Workshop by Mike Roberts | Location: Room 101D
9:00AM - 5:00PM: AI for Content Creation Workshop by Krishna Kumar Singh (Organizer), Kai Zhang (Keynote) | Location: Room Grand 1A
10:45AM - 12:15PM: MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data by Paul Borne-Pons, Mikolaj Czerkawski, Rosalie Martin, Romain Rouffet | Location: Room 209 A-C
10:55AM - 11:25AM: 1st Workshop on 3D-LLM/VLA Keynote by Sai Bi | Location: Room 106A
11:30AM - 12:30PM: EOPose : Exemplar-based Object Reposing Using Generalized Pose Correspondences Poster by Sarthak Mehrotra, Rishabh Jain, Mayur Hemani, Balaji Krishnamurthy, Mausoom Sarkar.
11:30AM - 12:30PM: VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors Poster by Juil Koo, Paul Guerrero, Chun-Hao Huang, Duygu Ceylan, Minhyuk Sung.
1:00PM - 5:00PM | The 4th Workshop on Transformers for Vision (T4V) Keynote by Yuheng Li | Location: Room 209 A-C
1:15PM - 3:00PM: Future of Generative AI Research Keynote and Discussion by Eli Shechtman | Location: Room 207 A-D
3:10PM - 3:45PM: Understanding Generative AI Capabilities in Everyday Image Editing Tasks by Viet Lai, Trung Bui | Location: Room 207 A-D
Friday, June 13
Oral Presentation | 9:00AM - 9:15AM | Davidson Ballroom
Removing Reflections from RAW Photos by Eric Kee, Adam Pikielny, Kevin Blackburn-Matzen, Marc Levoy.
Expo Hall | 10:00AM - 6:30PM
Stop by to speak with our Adobe Recruiting team, network with our Researchers, and discover our cutting-edge work.
Poster Session 1 | 10:30AM - 12:30PM | Hall D
[Highlight Paper] Polarized Color Screen Matting by Kenji Enomoto, Scott Cohen, Brian Price, TJ Rhodes.
Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable by Xin Jin, Simon Niklaus, Zhoutong Zhang, Zhihao Xia, Chun-Le Guo, Yuting Yang, Jiawen Chen, Chongyi Li.
Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization by Junying Wang, Jingyuan Liu, Xin Sun, Krishna Kumar Singh, Zhixin Shu, He Zhang, Jimei Yang, Nanxuan Zhao, Tuanfeng Y. Wang, Simon S. Chen, Ulrich Neumann, Jae Shin Yoon.
Exploring Temporally-Aware Features for Point Tracking by Inès Hyeonsu Kim, Seokju Cho, Gabriel Huang, Jung Yi, Joon-Young Lee, Seungryong Kim.
Motion Modes: What Could Happen Next? by Karran Pandey, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy J. Mitra, Paul Guerrero.
PreciseCam: Precise Camera Control for Text-to-Image Generation by Edurne Bernal-Berdun, Ana Serrano, Belen Masia, Matheus Gadelha, Yannick Hold-Geoffroy, Xin Sun, Diego Gutierrez.
Removing Reflections from RAW Photos by Eric Kee, Adam Pikielny, Kevin Blackburn-Matzen, Marc Levoy.
ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion by Nissim Maruani, Wang Yifan, Matthew Fisher, Pierre Alliez, Mathieu Desbrun.
Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions by Ting-Hsuan Liao, Yi Zhou, Yu Shen, Chun-Hao P. Huang, Saayan Mitra, Jia-Bin Huang, Uttaran Bhattacharya.
SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces by Sumit Chaturvedi, Mengwei Ren, Yannick Hold-Geoffroy, Jingyuan Liu, Julie Dorsey, Zhixin Shu.
VideoGigaGAN: Towards Detail-rich Video Super-Resolution by Yiran Xu, Taesung Park, Richard Zhang, Yang Zhou, Eli Shechtman, Feng Liu, Jia-Bin Huang, Difan Liu.
Poster Session 2 | 4:00PM - 6:00PM | Hall D
[Highlight Paper] Multitwine: Multi-Object Compositing with Text and Layout Control by Gemma Canet Tarrés, Zhe Lin, Zhifei Zhang, He Zhang, Andrew Gilbert†, John Collomosse†, Soo Ye Kim†.
[Highlight Paper] Seurat: From Moving Points to Depth by Seokju Cho, Gabriel Huang, Seungryong Kim, Joon-Young Lee.
Generative Image Layer Decomposition with Visual Effects by Jinrui Yang, Qing Liu, Yijun Li, Soo Ye Kim, Daniil Pakhomov, Mengwei Ren, Jianming Zhang, Zhe Lin, Cihang Xie, Yuyin Zhou.
LIM: Large Interpolator Model for Dynamic Reconstruction by Remy Sabathier, Niloy J. Mitra, David Novotny.
OmniStyle: Filtering High Quality Style Transfer Data at Scale by Ye Wang, Ruiqi Liu, Jiang Lin, Fei Liu, Zili Yi, Yilin Wang, Rui Ma.
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation by Hyeonho Jeong, Chun-Hao Paul Huang, Jong Chul Ye, Niloy J. Mitra, Duygu Ceylan.
TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting by Liangbin Xie, Daniil Pakhomov, Zhonghao Wang, Zongze Wu, Ziyan Chen, Yuqian Zhou, Haitian Zheng, Zhifei Zhang, Zhe Lin, Jiantao Zhou, Chao Dong.
Saturday, June 14
Expo Hall | 10:00AM - 6:30PM
Stop by to speak with our Adobe Recruiting team, network with our Researchers, and discover our cutting-edge work.
Poster Session 3 | 10:30AM - 12:30PM | Hall D
[Highlight Paper] UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics by Xi Chen, Zhifei Zhang, He Zhang, Yuqian Zhou, Soo Ye Kim, Qing Liu, Yijun Li, Jianming Zhang, Nanxuan Zhao, Yilin Wang, Hui Ding, Zhe Lin, Hengshuang Zhao.
Composing Parts for Expressive Object Generation by Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni, R. Venkatesh Babu, Srikrishna Karanam.
MaDCoW: Marginal Distortion Correction for Wide-Angle Photography with Arbitrary Objects by Kevin Zhang, Jia-Bin Huang, Jose Echevarria, Stephen DiVerdi, Aaron Hertzmann.
Yo’Chameleon: Personalized Vision and Language Generation by Thao Nguyen, Krishna Kumar Singh, Jing Shi, Trung Bui,Yong Jae Lee, Yuheng Li.
Oral Presentation | 3:15PM - 3:30PM | Karl Dean Grand Ballroom
Craftsman: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner by Weiyu Li, Jiarui Liu, Hongyu Yan, Rui Chen, Yixun Liang, Xuelin Chen, Ping Tan, Xiaoxiao Long†.
Demo | 5:00PM - 7:00PM | Hall D
Grounding Pixels in Facts: Distilled Knowledge Retrieval for Factual Text-to-Video Generation by Daniel Lee, Arjun Chandra, Yang Zhou, Yunyao Li, Simone Conia.
Poster Session 4 | 5:00PM - 7:00PM | Hall D
[Highlight Paper] Improving Personalized Search with Regularized Low-Rank Parameter Updates by Fiona Ryan, Josef Sivic, Fabian Caba Heilbron, Judy Hoffman, James Rehg, Bryan Russell.
DiffCR: Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers by Haoran You, Connelly Barnes, Yuqian Zhou, Yan Kang, Zhenbang Du, Wei Zhou, Lingzhi Zhang, Yotam Nitzan, Xiaoyang Liu, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi, Yingyan Celine Lin.
Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects by Amir Barda, Matheus Gadelha, Vladimir Kim, Noam Aigerman, Amit Haim Bermano, Thibault Groueix.
Generative Video Propagation by Shaoteng Liu, Tianyu Wang, Jui-Hsien Wang, Qing Liu, Zhifei Zhang, Joon-Young Lee, Yijun Li, Bei Yu, Zhe Lin, Soo Ye Kim†, Jiaya Jia†.
ObjectMover: Generative Object Movement with Video Prior by Xin Yu, Tianyu Wang, Soo Ye Kim, Paul Guerrero, Xi Chen, Qing Liu, Zhe Lin, Xiaojuan Qi.
TransPixeler: Advancing Text-to-Video Generation with Transparency by Luozhou Wang, Yijun Li, ZhiFei Chen, Jui-Hsien Wang, Zhifei Zhang, He Zhang, Zhe Lin, Ying-Cong Chen.
Video-Guided Foley Sound Generation with Multimodal Controls by Ziyang Chen, Prem Seetharaman, Bryan Russell, Oriol Nieto, David Bourgin, Andrew Owens, Justin Salamon.
VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors by Juil Koo, Paul Guerrero, Chun-Hao Huang, Duygu Ceylan, Minhyuk Sung.
Sunday, June 15
Expo Hall | 10:00AM - 3:00PM
Stop by to speak with our Adobe Recruiting team, network with our Researchers, and discover our cutting-edge work.
Poster Session 5 | 10:30AM - 12:30PM | Hall D
EntitySAM: Segment Everything in Video by Mingqiao Ye, Seoung Wug Oh, Lei Ke, Joon-Young Lee.
FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity by Hang Hua, Qing Liu, Lingzhi Zhang, Jing Shi, Soo Ye Kim, Zhifei Zhang, Yilin Wang, Jianming Zhang, Zhe Lin, Jiebo Luo.
The Photographer’s Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers by Daiqing Qi, Handong Zhao, Jing Shi, Simon Jenni, Yifei Fan, Franck Dernoncourt, Scott Cohen, Sheng Li.
Panel | 1:30PM | Exhibit Hall
CVPR AI Art Gallery Panel moderated by Aaron Hertzmann.
Poster Session 6 | 4:00PM - 6:00PM | Hall D
[Highlight Paper] TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction by Aishwarya Agarwal, Srikrishna Karanam, Vineet Gandhi.
AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models by Sohan Patnaik, Rishabh Jain, Balaji Krishnamurthy, Mausoom Sarkar.
GenVDM: Generating Vector Displacement Maps From a Single Image by Yuezhi Yang, Qimin Chen, Vladimir Kim, Siddhartha Chaudhuri, Qixing Huang, and Zhiqin Chen.
MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis by Tianyu Wang, Jianming Zhang, Haitian Zheng, Zhihong Ding, Scott Cohen, Zhe Lin, Wei Xiong, Chi-Wing Fu, Luis Figueroa†, Soo Ye Kim†.
Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy by Aditya Ganeshan, Thibault Groueix, Paul Guerrero, Radomir Mech, Matthew Fisher, Daniel Ritchie.
ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models by Ozgur Kara, Krishna Kumar Singh, Feng Liu, Duygu Ceylan, James M. Rehg, Tobias Hinz.
SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction by Zhengyuan Li, Kai Cheng, Anindita Ghosh, Uttaran Bhattacharya, Liangyan Gui, Aniket Bera.
About Adobe Research
Adobe Research is a team of world-class research scientists, engineers, artists, and designers uniting cutting-edge academic discovery with industry impact. We shape experimental ideas into innovative technologies for Adobe’s products, building the company’s reputation as a pioneer in content and data intelligence. Our team collaborates with colleagues at universities around the world, presenting publications at international conferences. Our collaborative projects advance the state of the art across a range of 12 research areas:
Join #AdobeLife
Adobe Careers | We believe that great ideas come from everywhere in the company, and the next one could be yours. Bring your talents to Adobe and help us create the future.
Adobe Research Internships | Apply early and apply often — work by Adobe Research interns is presented at leading academic conferences and may be integrated into Adobe’s software, reaching millions of screens across the globe.
Adobe For All | At Adobe, we believe that when people feel respected and included they can be more creative, innovative, and successful.
Adobe Benefits | Check out how we're supporting our people to create better experiences.
Keep up with #AdobeLife | Adobe Life Blog, LinkedIn, Instagram