Adobe Research creates new technologies in computer vision and imaging, including breakthroughs in image search, organization, editing, and generation. Our scientists and engineers tackle problems such as object, text, and face detection, segmentation, person recognition, image quality, captioning, denoising, and deblurring. Many of our approaches tap into deep learning to empower creative image editing.
We also focus on video enhancement, analysis, synthesis, and understanding. We are interested in research problems such as video object segmentation, stabilization, generation, recognition, joint audio and video understanding, compression, and delivery. We seek to empower our users to create compelling video content and help our customers to maximize the value of their videos through next-generation experiences, analytics, and data-driven enhancement to video creation and monetization.
Meet some of our researchersView More
View our latest publicationsView More
An Image is Worth Multiple Words: Multi-attribute Inversion for Constrained Text-to-Image Synthesis
Agarwal, A., Karanam, S., Shukla, T., Srinivasan, B. (Feb. 28, 2025)
Winter Conference on Applications of Computer Vision (WACV)
AlignIT: Enhancing Prompt Alignment in Customization of Text-to-Image Models
Agarwal, A., Karanam, S., Srinivasan, B. (Feb. 28, 2025)
Winter Conference on Applications of Computer Vision (WACV)
ActAnywhere: Subject-Aware Video Background Generation
Pan, B., Xu, Z., Huang, C., Singh, K., Zhou, Y., Guibas, L., Yang, J. (Dec. 10, 2024)
Neural Information Processing Systems (NeurIPS)
Create 3D Photos with a Still Image
Project Moving Stills, led by researcher Long Mai, enables any photograph to be turned into a “live photo,” animating the image in 3D and simulating a realistic effect of flying through the photo. This experimental effort uses deep learning to generate videos from a single still image.
