I don't know anyone (except Marie Kondo) who likes to clean/organize a messy room. So, how can we build machines that can do this for us? At #CVPR2025, we will present LEGO-Net, a data-driven method for LEarning reGular rearrangement of Objects in messy rooms. #CVPR2023 Thread🧵

Happy to share our #ICCV2023 work😊 We show compositional 3D scene generation from 2D scene layouts. Joint effort with a great team Jeong Joon Park Despoina Paschalidou 𝕏ingguang Yan Gordon Wetzstein Leonidas Guibas Andrea Tagliasacchi 🇨🇦

🌟📢 Welcome aboard to our new Michigan AI faculty joining us this fall: Elizabeth Bondi-Kelly (Elizabeth Bondi-Kelly), David Jurgens (David Jurgens), Jeong Joon Park (Jeong Joon Park), and Alexander Rodríguez (Alexander Rodríguez) )!! cse.engin.umich.edu/stories/cse-we…

Sherwin Sherwin Bahmani will be presenting our #ICCV2023 work CC3D today afternoon (Oct 4th 02:30-04:30 PM). If you're interested in this work or want to have a chat with us, please come visit our poster at "Foyer Sud" - 088!

Eric Chan Eric Chan will be presenting our #ICCV2023 work GeNVS at the "Generative AI 1" Oral session today (Oct. 4th 04:30-06:00 PM)! If you're interested in this work or want to chat with us, come visit our poster 190 in Room "Foyer Sud."

At #ICCV23 at Paris — email me if you want to catch up or chat about research! I'm looking for PhD students, PostDocs, and Visitors at University of Michigan. For PhD, please see details on my website. For PostDocs, seeking a candidate with Machine Learning or Comp. Neuroscience background.

📢📢📢 thrilled to announce "𝟒𝐃-𝐟𝐲: 𝐓𝐞𝐱𝐭-𝐭𝐨-𝟒𝐃 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐔𝐬𝐢𝐧𝐠 𝐇𝐲𝐛𝐫𝐢𝐝 𝐒𝐜𝐨𝐫𝐞 𝐃𝐢𝐬𝐭𝐢𝐥𝐥𝐚𝐭𝐢𝐨𝐧 𝐒𝐚𝐦𝐩𝐥𝐢𝐧𝐠" sherwinbahmani.github.io/4dfy Way to start Sherwin Bahmani 🎉 PhD co-advised with David Lindell at #UofT.

📢 Presenting 𝐅𝐀𝐑: 𝐅𝐥𝐞𝐱𝐢𝐛𝐥𝐞, 𝐀𝐜𝐜𝐮𝐫𝐚𝐭𝐞 𝐚𝐧𝐝 𝐑𝐨𝐛𝐮𝐬𝐭 𝟔𝐃𝐨𝐅 𝐑𝐞𝐥𝐚𝐭𝐢𝐯𝐞 𝐂𝐚𝐦𝐞𝐫𝐚 𝐏𝐨𝐬𝐞 𝐄𝐬𝐭𝐢𝐦𝐚𝐭𝐢𝐨𝐧 #CVPR2024 FAR builds upon complimentary Solver and Learning-Based works yielding accurate *and* robust pose! crockwell.github.io/far/

📢📢📢 TC4D: Trajectory-Conditioned Text-to-4D Generation Homepage: sherwinbahmani.github.io/tc4d Lead by Sherwin Bahmani, with collaborators Xian Liu Yifan Wang Ivan Skorokhodov Victor Rong Ziwei Liu Xihui Liu Jeong Joon Park Sergey Tulyakov Gordon Wetzstein Andrea Tagliasacchi (🇮🇹ECCV) David Lindell

Last week's @LerobotHF Tech Talk is now available on YouTube! Check it out 👉youtu.be/rcYyhJgG5Ds Jeong Joon Park presents This&That, a method for using language and *gestures* to command a robot!