Novedades 2023

Estimados,

• Va una lista de 15 artículos que cubren una buena parte de los temas del curso. Cada artículo tiene asociado un link con al pdf del artículo, y uno a más links a implementaciones en caso de que quieran correr algo ustedes mismos (no es requisito pero obviamente aporta).

• La idea es que se vayan viendo cuáles les interesan. El lunes 20 a las 18h se abre una actividad EVA para que registren su selección.  Cada uno de los artículos podrá ser elegido por a lo sumo tres personas, y estos cupos se irán agotando a medida que ustedes los vayan eligiendo. Por esta razón, sería bueno que se armen una lista de preferencia de tres o cuatro artículos antes de ingresar al sistema, por si el artículo que querían ya no está disponible. 

• Como les dijimos, si tienen en mente otro artículo que quisieran presentar, les pedimos que nos lo manden por mail el lunes de mañana para inspeccionarlo. Para que accedamos a autorizarlo, el artículo tiene que cumplir:

1. Estar dentro de las temas del curso
2. Haber sido publicado en una revista o conferencia de prestigio del área. A modo de ejemplo:

• Conferencias: CVPR, ICCV, ECCV, WACV, Neurips, ICML, ICLR, ...
• Revistas: IEEE PAMI, IJCV, ACM TOG, Nature Machine Intelligence

• Les recordamos que el trabajo es individual. 

Cualquier consulta nos escriben.

Saludos,

Pablo

------------------------------------------------------

Nerf (Neural Radiance Fields)

1 .Nerf

Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2021). Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1), 99-106.

https://dl.acm.org/doi/abs/10.1145/3503250

https://github.com/bmild/nerf

https://github.com/facebookresearch/pytorch3d/tree/main/projects/nerf

Segmentación

2. Segment anything

Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., ... & Girshick, R. (2023). Segment anything. ICCV 2023. 

https://openaccess.thecvf.com/content/ICCV2023/papers/Kirillov_Segment_Anything_ICCV_2023_paper.pdf

https://github.com/facebookresearch/segment-anything

Detección de objetos

3. YOLOv7

Wang, C. Y., Bochkovskiy, A., & Liao, H. Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7464-7475).
https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_YOLOv7_Trainable_Bag-of-Freebies_Sets_New_State-of-the-Art_for_Real-Time_Object_Detectors_CVPR_2023_paper.pdf

https://github.com/WongKinYiu/yolov7

Vision Transfomers

4. DETR

Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020, August). End-to-end object detection with transformers. In European conference on computer vision (pp. 213-229). Cham: Springer International Publishing.

https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123460205.pdf

https://github.com/facebookresearch/detr

https://huggingface.co/docs/transformers/v4.35.2/en/model_doc/detr

5. ViT

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., ... & Houlsby, N. (2020, October). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations.

https://openreview.net/pdf?id=YicbFdNTTy

https://huggingface.co/docs/transformers/model_doc/vit

https://github.com/google-research/vision_transformer

VAEs

6. NVAE

Vahdat, A., & Kautz, J. (2020). NVAE: A deep hierarchical variational autoencoder. Advances in neural information processing systems, 33, 19667-19679.

https://proceedings.neurips.cc/paper/2020/file/e3b21256183cf7c2c7a66be163579d37-Paper.pdf

https://github.com/NVlabs/NVAE

7. VQ-VAE

Razavi, A., Van den Oord, A., & Vinyals, O. (2019). Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems, 32.

https://papers.nips.cc/paper_files/paper/2019/file/5f8e2fa1718d1bbcadf1cd9c7a54fb8c-Paper.pdf

https://github.com/rosinality/vq-vae-2-pytorch

https://github.com/google-deepmind/sonnet

8. Masked Autoencoders

He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 16000-16009).

https://openaccess.thecvf.com/content/CVPR2022/papers/He_Masked_Autoencoders_Are_Scalable_Vision_Learners_CVPR_2022_paper.pdf

https://github.com/facebookresearch/mae

Normalizing Flows

9. Glow

Kingma, D. P., & Dhariwal, P. (2018). Glow: Generative flow with invertible 1x1 convolutions. Advances in neural information processing systems, 31.

https://proceedings.neurips.cc/paper/2018/file/d139db6a236200b21cc7f752979132d0-Paper.pdf

https://github.com/openai/glow

10. SRFlow

Lugmayr, A., Danelljan, M., Van Gool, L., & Timofte, R. (2020). Learning the super-resolution space with normalizing flow. ECCV, Srflow.

https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123500698.pdf

https://github.com/andreas128/SRFlow

GANs

11. StyleGan 

Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 4401-4410).

https://openaccess.thecvf.com/content_CVPR_2019/papers/Karras_A_Style-Based_Generator_Architecture_for_Generative_Adversarial_Networks_CVPR_2019_paper.pdf

https://github.com/NVlabs/stylegan

https://proceedings.neurips.cc/paper_files/paper/2021/file/076ccd93ad68be51f23707988e934906-Paper.pdf

https://github.com/NVlabs/stylegan3

Diffusion Models

13. Deep unsupervised learning using nonequilibrium thermodynamics

Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015, June). Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning (pp. 2256-2265). PMLR.

http://proceedings.mlr.press/v37/sohl-dickstein15.pdf

https://github.com/Sohl-Dickstein/Diffusion-Probabilistic-Models

14. Denoising diffusion probabilistic models

Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in neural information processing systems, 33, 6840-6851.
https://proceedings.neurips.cc/paper_files/paper/2020/file/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf

https://github.com/hojonathanho/diffusion

15. ControlNet

Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 3836-3847).

https://openaccess.thecvf.com/content/ICCV2023/papers/Zhang_Adding_Conditional_Control_to_Text-to-Image_Diffusion_Models_ICCV_2023_paper.pdf

https://github.com/lllyasviel/ControlNet