CSE590V: Vision Seminar

CSE 590V: Vision Seminar

Fall 2022

Course description

CSE 590V is a seminar/reading group focused on recent work in computer vision and graphics. We will cover papers from recent and upcoming conferences related to computer vision (CVPR, ICCV, ECCV, SIGGRAPH, NeurIPS, ICLR, ICML). We will also have guest lectures talking about their research. The seminar is open to everyone. We especially encourage first year graduate students who may be considering research in computer vision or related areas to participate. Please visit here for basic course information and links to the webs for earlier quarters.

Logistics

Time: Mondays @ 12:00pm - 1:00pm

Zoom Link: Here

Organizers: Johanna Karras (jskarras @ cs washington edu) and Mengyi Shan (shanmy @ cs washington edu)

Schedule

Date	Topic	Presenters	Papers	Recording	Slides
October 3	First Meeting	No Speakers
October 1	Diffusion Model Tutorial	Yifan Wang, Benlin Liu	Denoising Diffusion Probabilistic Models Diffusion Models Beat GANs on Image Synthesis	Link	Yifan Benlin
October 17	Portrait Animation	Mengyi Shan, Alice Gao	Implicit Warping for Animation with Image Sets MegaPortraits: One-shot Megapixel Neural Head Avatars	Link	Link
October 24	Video Synthesis with Diffusion Models	Johanna Karras	Video Diffusion Models Flexible Diffusion Modeling of Long Videos Imagen Video: High Definition Video Generation with Diffusion Models	Link
October 31		Jingwei Ma	Imagic: Text-Based Real Image Editing with Diffusion Models	Link	Link
November 7	CVPR DDL (No seminar)
November 14	CVPR Supp DDL (No seminar)
November 21	Seminar Canceled
November 28		Chung-Yi Weng, Bowei Chen	Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise Learning Continuous Implicit Representation for Near-Periodic Patterns	Link
December 5	Guest Speaker	Jia-Bin Huang	3D Photography using Context-aware Layered Depth Inpainting Consistent Video Depth Estimation Space-time Neural Irradiance Fields for Free-Viewpoint Video Dynamic View Synthesis from Dynamic Monocular Video ClimateNeRF: Physically-based Neural Rendering for Extreme Climate Synthesis	Link