| 1/9/23 | Lecture-1-Introduction
[Video of Presentation] | Dr. Shah | |
| 1/11/23 | Lecture-2-Transformer Introduction
[Video of Presentation] | Dr. Shah | |
| 1/16/23 | Martin Luther King Jr. Day No Class | | |
| 1/18/23 | Lecture-3 DALL-E & CLIP
[Video of Presentation] | Dr. Shah | |
| 1/23/23 | Lecture-4 diffusion models-Part-I
[Video of Presentation] | Dr. Shah | |
| 1/25/23 | Lecture-5-diffusion_models-Part-II
[Video of Presentation] | Dr. Shah | |
| 1/30/23 | Discussions on the topics covered so far | | |
| 2/1/23 | Paper-1 GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
[Presentation PDF], [Video of Presentation] | Group-5 (Ahmed Abd El-Rahman, Joseph Green, Rajat Modi, Muhammad Shahbaz, Chandra Teja Tiriveedhi) | |
| 2/6/23 | Paper-2 Hierarchical Text-Conditional Image Generation with CLIP Latents (Dall-e-2)
[Presentation PDF], [Video of Presentation] | Group-6 (Jeffrey Chan-Santiago, Kevin Samms, Qingyuan Li, Zhaoning Wang) | |
| 2/8/23 | Paper-3 High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion)
[Presentation PDF], [Video of Presentation] | Group-4 (Ronald Campos, Muhammad Asad Haider, Suneet Tipirneni, Stefan Werleman) | |
| 2/13/23 | Paper-4 Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Imagen)
[Presentation PDF], [Video of Presentation] | Group-9 (Chase Walker, Dominic Simon, Ilkin Sevgi Isler, Shehreen Azad) | |
| 2/15/23 | Paper-5 DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
[Presentation PDF], [Video of Presentation] | Group-8 (Shane Davis, Mitchell Klingler, Joseph Fioresi, Nyle Siddiqui) | |
| 2/20/23 | Project Presentations | | |
| 2/22/23 | Project Presentations Continue | | |
| 2/27/23 | Paper-6 HUMAN MOTION DIFFUSION MODEL
[Presentation PDF], [Video of Presentation] | Group-4 (Ronald Campos, Muhammad Asad Haider, Suneet Tipirneni, Stefan Werleman) | |
| 3/1/23 | Paper-9 Bao, Fan, et al. "Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models." arXiv preprint arXiv:2201.06503 (2022).
[Presentation PDF], [Video of Presentation] | Group-3 (Joshua Foldes, Vijay Prakash Reddy Kovuru, Sirshapan Mitra, Austin Roberts) | |
| 3/6/23 | Paper-8 Person Image Synthesis via Denoising Diffusion Model
[Presentation PDF], [Video of Presentation] | Group-1 (Prudvi Kamtam, Manu S. Pillai, Mukund Dhar, Adeel Yousaf) | |
| 3/8/23 | Paper-7 DiffusionDet: Diffusion Model for Object Detection
[Presentation PDF], [Video of Presentation] | Group-2 (Ethan Legum, Melody Halbert, Julie Wan, Nayoun Ham) | |
| 3/13/23 | Spring Break | | |
| 3/15/23 | Sprig Break | | |
| 3/20/23 | No class. Group 3 will come to office hours for trial presentation | | |
| 3/22/23 | Paper-10 Ho, Jonathan, et al. "Cascaded Diffusion Models for High Fidelity Image Generation." J. Mach. Learn. Res. 23 (2022): 47-1.
[Presentation PDF], [Video of Presentation] | Group-3 (Joshua Foldes, Vijay Prakash Reddy Kovuru, Sirshapan Mitra, Austin Roberts) | |
| 3/27/23 | Paper-11 Gu, Shuyang, et al. "Vector quantized diffusion model for text-to-image synthesis." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
[Presentation PDF], [Video of Presentation] | Group-1 (Prudvi Kamtam, Manu S. Pillai, Mukund Dhar, Adeel Yousaf) | |
| 3/29/23 | Paper-12 Saharia, Chitwan, et al. "Image super-resolution via iterative refinement." arXiv preprint arXiv:2104.07636 (2021)
[Presentation PDF], [Video of Presentation] | Group-2 (Ethan Legum, Melody Halbert, Julie Wan, Nayoun Ham) | |
| 4/3/23 | Project Presentation (Groups 5, 6, 8, and 9) | | |
| 4/5/23 | Project Presentation Continue (Groups 1, 2, 3, and 4) | | |
| 4/10/23 | Paper-13 Amit, Tomer, et al. "Segdiff: Image segmentation with diffusion probabilistic models." arXiv preprint arXiv:2112.00390 (2021). [Presentation PDF ], [Video of Presentation] | Group-9 (Chase Walker, Dominic Simon, Ilkin Sevgi Isler, Shehreen Azad) | |
| 4/12/23 | Paper-14 Harvey, William, et al. "Flexible Diffusion Modeling of Long Videos." arXiv preprint arXiv:2205.11495 (2022).
[Presentation PDF], [Video of Presentation] | Group-8 (Shane Davis, Mitchell Klingler, Joseph Fioresi, Nyle Siddiqui) | |
| 4/17/23 | Paper-15 Meng, Chenlin, et al. "Sdedit: Guided image synthesis and editing with stochastic differential equations." InternationalConference on Learning Representations. 2021.
[Presentation PDF ], [Video of Presentation] | Group-5 (Ahmed Abd El-Rahman, Joseph Green, Rajat Modi, Muhammad Shahbaz, Chandra Teja Tiriveedhi) | |
| 4/19/23 | Paper-16 Lugmayr, Andreas, et al. "Repaint: Inpainting using denoising diffusion probabilistic models." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
[Presentation PDF], [Video of Presentation] | Group-6 (Jeffrey Chan-Santiago, Kevin Samms, Qingyuan Li, Zhaoning Wang) | |
| 4/24/23 | End of classes [class attendance is optional on this date. If you want to attend and want to discuss your project and other matters, send an email before the class] | | |
| 4/26/23 | Final Project Presentation (1:00 pm to 3:50 pm) | | |
| Potential Papers | - GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- Hierarchical Text-Conditional Image Generation with CLIP Latents (Dall-e-2)
- High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion)
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Imagen)
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
- HUMAN MOTION DIFFUSION MODEL
- DiffusionDet: Diffusion Model for Object Detection
- Person Image Synthesis via Denoising Diffusion Model
- Bao, Fan, et al. "Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models." arXiv preprint arXiv:2201.06503 (2022).
- Ho, Jonathan, et al. "Cascaded Diffusion Models for High Fidelity Image Generation." J. Mach. Learn. Res. 23 (2022): 47-1.
- Gu, Shuyang, et al. "Vector quantized diffusion model for text-to-image synthesis." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
- Saharia, Chitwan, et al. "Image super-resolution via iterative refinement." arXiv preprint arXiv:2104.07636 (2021)
- Amit, Tomer, et al. "Segdiff: Image segmentation with diffusion probabilistic models." arXiv preprint arXiv:2112.00390 (2021).
- Harvey, William, et al. "Flexible Diffusion Modeling of Long Videos." arXiv preprint arXiv:2205.11495 (2022).
- Meng, Chenlin, et al. "Sdedit: Guided image synthesis and editing with stochastic differential equations." InternationalConference on Learning Representations. 2021.
- Lugmayr, Andreas, et al. "Repaint: Inpainting using denoising diffusion probabilistic models." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.
- Molad, Eyal, et al., "Dreamix: Video Diffusion Models are General Video Editors" Feb 2, 2023. - Additinal Link: https://dreamix-video-editing.github.io/
- Esser, Patrick, et al., "Structure and Content-Guided Video Synthesis with Diffusion Models." Feb 6, 2023.
| | |