Yawar Siddiqui
@yawarnihal
Followers
1K
Following
3K
Media
14
Statuses
525
Researcher in 3D Computer Vision at Meta. Views expressed are my own.
Munich, Bavaria
Joined April 2011
Tired of 3D asset generation approaches with baked in lighting effects? Our latest work, Meta 3D AssetGen, can generate high quality meshes with PBR materials given text prompts in seconds! https://t.co/qmTqYtfU4P The work was done with the amazing GenAI 3D team @AIatMeta
π£ New research from GenAI at Meta, introducing Meta 3D Gen: A new system for end-to-end generation of 3D assets from text in <1min. Meta 3D Gen is a new combined AI system that can generate high-quality 3D assets, with both high-resolution textures and material maps end-to-end,
5
12
155
Join the Project Aria Team TODAY at "Egocentric Body Motion Tracking, Synthesis and Action Recognition" @ICCVConference in Ballroom C on level 4. π
Monday, October 20 β°1pm-5pm in Ballroom C on Level 4 π https://t.co/K3gZH4pFEx
@meta_aria's own @LingniMa will present a
0
7
13
Join us at the 4th Project Aria tutorial on Monday, October 20th at #ICCV2025! I'll also be giving a talk there on the stuff I've been working on recently :)
Join the Project Aria team at #ICCV2025 for The Fourth Hands-on Egocentric Research Tutorial with Project Aria π π
Monday, Oct 20th π8am-12pm πRoom 326B Featuring inspiring talks from @rapideRobot, @LingniMa, @danfei_xu, @bowenwen_me, and more! π Learn more
0
3
17
π’ Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a
19
74
247
Checkout MapAnything! A metric VGGT like model that can take additional inputs like calibration, poses or depth!
Meet MapAnything β a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art
0
0
14
Meet MapAnything β a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art
29
130
723
Check out our #ICCV2025 paper VertexRegen! Instead of the typical incomplete meshes you get with autoreg mesh gen, VertexRegen generates progressively more detailed meshes as the generated sequence gets longer. https://t.co/hUW5vQDQTt Great work by https://t.co/dYNudbBBlj
3
36
346
Congratulations @w_zielonka! π₯³π₯³
Yesterday marked a very important milestone in my life. I successfully defended my PhD under the supervision of Prof. @JustusThies π. It has been an incredible four-year journey, and Iβm deeply grateful for the opportunity and trust that Justus placed in me as his student.
0
0
2
Looking for a visual computing researcher to join our team working on editing of human-centric videos with diffusion models. We are training a DiT for v2v lipsync+controls, as well as seamless operations on video (frame addition/removal). Remote from Europe. DM or comment :)
1
4
21
Happy to report that AllTracker was accepted to #ICCV2025! The twists and turns and methodical experimentation here took at least 12 months in all. Super hard project, though in retrospect our solution is pretty simple. code: https://t.co/hYgFbQhnMv paper:
arxiv.org
We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing point tracking...
AllTracker: Efficient Dense Point Tracking at High Resolution If you're using any point tracker in any project, this is likely a drop-in upgradeβimproving speed, accuracy, and density, all at once.
4
11
102
Thrilled and honored to receive the Best Paper Award at #CVPR2025! Huge thanks to my fantastic collaborators @MinghaoChen23, @n_karaev, Andrea Vedaldi, Christian Rupprecht, and @davnov134. Could not be there without you!
40
18
477
π’π’ Weβll be presenting MeshArt tomorrow morning (Friday 13.06) in the poster session at ExHall D Poster #42 from 10:30-12:30. Come and chat about articulated 3D mesh genereation or any 3D generative stuff! Project page: https://t.co/yHqazRNydx
3
27
182
Iβll be in Nashville for #CVPR this week presenting 2 papers. Keen to connect with people interested in Generative AI and 3D Computer Vision. If you see me at the venue & are interested in connecting for projects, research positions or just a chat, feel free to say hi!
0
8
12
Aria Gen 2 glasses mark a significant leap in wearable technology, offering enhanced features and capabilities that cater to a broader range of applications and researcher needs. We believe researchers from industry and academia can accelerate their work in machine perception,
45
196
975
This looks amazing! Great work @Peter4AI !!
π’ IntrinsiX: High-Quality PBR Generation using Image Priors π’ From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation. We first train
1
0
7
π’ IntrinsiX: High-Quality PBR Generation using Image Priors π’ From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation. We first train
1
57
249
Tomorrow in our TUM AI - Lecture Series we'll have Andrea Tagliasacchi (@taiyasaki), SFU. He'll talk about "ππππ’ππ§π π
π¨ππ¦: ππππ₯-ππ’π¦π ππ’ππππ«ππ§ππ’πππ₯π πππ² ππ«πππ’π§π ". Live Stream: https://t.co/QySV934V7O 5pm GMT+1 / 9am PST (Mon Mar 24th)
2
23
191
Check out Chris' work on promptable SceneScript using infilling transformers!
Check out our extension of SceneScript to human-in-the-loop local corrections! Our method leverages infilling techniques from NLP to refine a 3D scene in a "one-click fix" workflow, enabling more accurate modeling of complex layouts. π° https://t.co/AA5JB438mT
0
0
11
Check out our extension of SceneScript to human-in-the-loop local corrections! Our method leverages infilling techniques from NLP to refine a 3D scene in a "one-click fix" workflow, enabling more accurate modeling of complex layouts. π° https://t.co/AA5JB438mT
1
7
24
Check out our #CVPR2025 papers on articulated mesh generation, 4d shape generation with dictionary neural fields, large-scale 3d scene generation and editing, and 3d editing! Congrats to @DaoyiGao, @xinyi092298, @ABokhovkin, @QTDSMQ, @ErkocZiya for their amazing work!
2
24
154
π₯³Excited to share my recent work at Meta, "PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models", which aims at compositional/part-level 3D generation and reconstruction from various modalities. Project page: https://t.co/oI2N44NfDB
3
48
233