Anagh Malik (@anagh_malik) 's Twitter Profile
Anagh Malik

@anagh_malik

CS PhD @UofT | 3D Computer Vision

ID: 173056941

linkhttps://anaghmalik.com calendar_today31-07-2010 08:54:38

215 Tweet

514 Takipรงi

250 Takip Edilen

Kai He (@kai__he) 's Twitter Profile Photo

๐Ÿš€ Introducing UniRelight, a general-purpose relighting framework powered by video diffusion models. ๐ŸŒŸUniRelight jointly models the distribution of scene intrinsics and illumination, enabling high-quality relighting and intrinsic decomposition from a single image or video.

Oncel Tuzel (@onceltuzel) 's Twitter Profile Photo

Come work with us! The Machine Learning Research (MLR) team at Apple is seeking a passionate AI researcher to work on Efficient ML algorithms: jobs.apple.com/en-us/details/โ€ฆ

Sotiris Nousias (@sotiris_no) 's Twitter Profile Photo

๐Ÿ“ธ Join us at ICCV 2025 for our workshop on Computer Vision with Single-Photon Cameras (CVSPC)! ๐Ÿ—“๏ธย  Sunday, Oct 19, AM โ€“ PM at the Hawai'i Convention Center. ๐Ÿ”— Website: cvspc.cs.pdx.edu. ๐Ÿ—ฃ๏ธ Invited Speakers: Mohit Gupta, Matthew O'Toole, Dongyu Du, David Lindell,

๐Ÿ“ธ Join us at ICCV 2025 for our workshop on Computer Vision with Single-Photon Cameras (CVSPC)!

๐Ÿ—“๏ธย  Sunday, Oct 19,  AM โ€“  PM at the Hawai'i Convention Center.

๐Ÿ”— Website: cvspc.cs.pdx.edu.

๐Ÿ—ฃ๏ธ Invited Speakers: Mohit Gupta, <a href="/mpotoole/">Matthew O'Toole</a>, <a href="/Dongyu_Du/">Dongyu Du</a>, <a href="/DaveLindell/">David Lindell</a>,
Aleksander Holynski (@holynski_) 's Twitter Profile Photo

Something fun we discovered: you can use #Genie3 to step into and explore your favorite paintings. Here's a short visit to Edward Hopper's "Nighthawks".

Felix Taubner (@taubnerfelix) 's Twitter Profile Photo

๐Ÿšจ Code Release for CAP4D๐Ÿงข Excited to share that we have released the inference code and weights for CAP4D! Visit github.com/felixtaubner/cโ€ฆ to generate an avatar and view it just like this one (yup that's me)

Esther Lin (@estheroate) 's Twitter Profile Photo

Every lens leaves a blur signatureโ€”a hidden fingerprint in every photo. In our new #TPAMI paper, we show how to learn it fast (5 mins of capture!) with Lens Blur Fields โœจ With it, we can tell apart โ€˜identicalโ€™ phones by their optics, deblur images, and render realistic blurs.

Every lens leaves a blur signatureโ€”a hidden fingerprint in every photo.

In our new #TPAMI paper, we show how to learn it fast (5 mins of capture!) with Lens Blur Fields โœจ

With it, we can tell apart โ€˜identicalโ€™ phones by their optics, deblur images, and render realistic blurs.
Samarth Sinha (@_sam_sinha_) 's Twitter Profile Photo

Canโ€™t believe itโ€™s been 3 whole years since i joined Luma AI ๐Ÿฅฐ Still feels like we are just getting started on our mission of solving computer vision and multimodality! The next year is going to be HUGE ๐Ÿ˜ (please ignore my profile pic on slack)

Canโ€™t believe itโ€™s been 3 whole years since i joined <a href="/LumaLabsAI/">Luma AI</a> ๐Ÿฅฐ

Still feels like we are just getting started on our mission of solving computer vision and multimodality! The next year is going to be HUGE ๐Ÿ˜

(please ignore my profile pic on slack)
Sherwin Bahmani (@sherwinbahmani) 's Twitter Profile Photo

Come hang out at our #ICCV2025 workshop on video models and their downstream applicationsโ€”like novel view synthesis and more! ๐ŸŒด๐Ÿน

Arthur Allshire (@arthurallshire) 's Twitter Profile Photo

super excited that we won the best student paper for videomimic! unfortunately i was packing in the hotel during the awards ceremony ๐Ÿ˜…

Felix Taubner (@taubnerfelix) 's Twitter Profile Photo

๐Ÿš€ Excited to release the full inference code of ๐ŸงขCAP4D๐Ÿงข! Generate animatable 4D avatars from any image(s) + driving video. ๐ŸคฉAlso works on stylized photos! ๐Ÿ‘‰ Code: github.com/felixtaubner/cโ€ฆ ๐Ÿ  Project page: felixtaubner.github.io/cap4d/

Michael Niemeyer (@mi_niemeyer) 's Twitter Profile Photo

How do we reconstruct a 3D scene from photos with varying exposures? Standard methods often fail, leaving you with blown-out colors or disturbing shadows. We're excited to introduce Neural Exposure Fields (NExF), our new work accepted at #NeurIPS2025! ๐Ÿงต

Moritz Reuss (@moritz_reuss) 's Twitter Profile Photo

VLAs have become the fastest-growing subfield in robot learning. So where are we now? After reviewing ICLR 2026 submissions and conversations at CoRL, I wrote an overview of the current state of VLA research with some personal takes: is.gd/1pqw9w

Felix Taubner (@taubnerfelix) 's Twitter Profile Photo

๐ˆ๐ง๐ญ๐ซ๐จ๐๐ฎ๐œ๐ข๐ง๐  ๐Ÿ†๐Œ๐•๐๐Ÿ’๐ƒ๐Ÿ† (๐’๐ˆ๐†๐†๐‘๐€๐๐‡ ๐€๐ฌ๐ข๐š ๐Ÿ๐ŸŽ๐Ÿ๐Ÿ“) MVP4D turns a single reference image into animatable 360-degree avatars! Project: felixtaubner.github.io/mvp4d/ Paper: arxiv.org/abs/2510.12785 ๐Ÿ””Code releases Nov 15th

Ruoshi Liu (@ruoshi_liu) 's Twitter Profile Photo

Everyone says they want general-purpose robots. We actually mean it โ€” and weโ€™ll make it weird, creative, and fun along the way ๐Ÿ˜Ž Recruiting PhD students to work on Computer Vision and Robotics UMD Department of Computer Science for Fall 2026 in the beautiful city of Washington DC!

Everyone says they want general-purpose robots.

We actually mean it โ€” and weโ€™ll make it weird, creative, and fun along the way ๐Ÿ˜Ž

Recruiting PhD students to work on Computer Vision and Robotics <a href="/umdcs/">UMD Department of Computer Science</a> for Fall 2026 in the beautiful city of Washington DC!
Stan Szymanowicz (@stanszymanowicz) 's Twitter Profile Photo

๐Ÿ“ข Bolt3D will be presented #ICCV2025 ! Catch us at the poster sessions: Main conference: Thu 23rd Oct 14.45-16.45 Invited workshops: FOUND workshop: Sun 19th Oct 11.30-12.30 AI3DCC workshop: Mon 20th Oct 10.10-11.00

Homanga Bharadhwaj (@mangahomanga) 's Twitter Profile Photo

I'll be joining the faculty Johns Hopkins University late next year as a tenure-track assistant professor in JHU Computer Science Looking for PhD students to join me tackling fun problems in robot manipulation, learning from human data, understanding+predicting physical interactions, and beyond!

I'll be joining the faculty <a href="/JohnsHopkins/">Johns Hopkins University</a> late next year as a tenure-track assistant professor in <a href="/JHUCompSci/">JHU Computer Science</a> 

Looking for PhD students to join me tackling fun problems in robot manipulation, learning from human data, understanding+predicting physical interactions, and beyond!