iro (@irolaina) profile picture
Joined October 2016
🚨 Deadline Extended! 🚨 The new deadline is April 25.​ We're looking for cutting-edge work on 3D-VLA models, LLM agents for 3D scene understanding, and more. 📢 Submit your paper now: openreview.net/group?id=thec…
Excited to announce the 1st Workshop on 3D-LLM/VLA at #CVPR2025! 🚀 @CVPR Topics: 3D-VLA models, LLM agents for 3D scene understanding, Robotic control with language. 📢 Call for papers: Deadline – April 20, 2025 🌐Details: 3d-llm-vla.github.io #llm #3d #Robotics #ai
7
38
3,728
Introducing SynCity 🌆 SynCity generates entire 3D worlds from a text prompt with no training or optimisation. It leverages pretrained 2D and 3D generators and generates scenes on a grid, tile by tile. The generated 3D environments are diverse, fully coherent, and navigable. 🧵👇
75
344
44
2,907
280,521
Excited to announce the 1st Workshop on 3D-LLM/VLA at #CVPR2025! 🚀 @CVPR Topics: 3D-VLA models, LLM agents for 3D scene understanding, Robotic control with language. 📢 Call for papers: Deadline – April 20, 2025 🌐Details: 3d-llm-vla.github.io #llm #3d #Robotics #ai
2
34
4
143
21,456
I am excited to share 'Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs', our method for directly predicting a 3D Gaussian Splat from a wide stereo pair of images without any camera poses. Website: splatt3r.active.vision/ ArXiv: arxiv.org/abs/2408.13912
1
1
1
190
We present SHAP-EDITOR, which tries to learn a universal feedforward editing function that can be applied to different objects within one second 🚀!! The demo is @huggingface !! abs: arxiv.org/abs/2312.09246 project page: silent-chen.github.io/Shap-E… demo: huggingface.co/spaces/silent…
2
7
31
10,990
📢🥳💫We were told this was impossible! Now public - accurate camera pose estimation for EPIC-KITCHENS, fully automatically. EPIC Fields: Marrying 3D Geometry and Video Understanding Dataset: epic-kitchens.github.io/epic… Paper: arxiv.org/abs/2306.08731 Trailer: youtu.be/RcacE26eObE
5
31
5
198
46,725
RealFusion 360◦ Reconstruction of Any Object from a Single Image abs: arxiv.org/abs/2302.10663
3
51
5
251
28,857
We are presenting our work “Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns” today at #NeurIPS2022. Joint work w/ @subhc4, @irolaina, @chrirupp and A. Vedaldi. Come see us and have a chat at poster 427 today 4-6pm!
1
6
50
The evidence is clear: open offices are bad for people and organizations. -27% more sick days -14% lower cognitive performance -70% less face-to-face interaction For the sake of health, productivity, and collaboration, let's design spaces with doors. nytimes.com/2022/09/08/opini…
74
926
211
3,833
Congratulations to @subhc4 @irolaina @chrirupp and Andrea Vedaldi on receiving the Best Student Paper Award at @BMVCconf 🎉🎉 Check out the paper: "The Curious Layperson" robots.ox.ac.uk/~vgg/researc…
BEST STUDENT PAPER AWARD The Curious Layperson: Fine-Grained Image Recognition without Expert Labels Subhabrata Choudhury, Iro Laina, Christian Rupprecht and Andrea Vedaldi University of Oxford
7
63
Can we possibly stop having the #CVPR2021 @CVPR reviewing periods that massively overlap with holidays? I reviewed all but 1 year since ~2010 and I'm fed up with working through Christmas and New Year. Especially bad for parents. Holiday=Holiday
4
17
7
241
We've observed AIs discovering complex tool use while competing in a simple game of hide-and-seek. They develop a series of six distinct strategies and counterstrategies, ultimately using tools in the environment to break our simulated physics: openai.com/blog/emergent-too…
69
1,009
266
2,918
NeurIPS, Black in AI and SOCML have all lost a lot of participants due to visa issues
35
84
23
369
CVPR 2019 received over 5100 submissions. NIPS and AAAI received ~ 5000 and 7000 submissions each. It's got to be tough being a PhD student these days!
Overleaf didn’t expect so many GAN papers being prepared for CVPR. 🐶
13
83
13
320