Ameesh Makadia (@kiamada) profile picture

Research Scientist, Google Research, NYC. https://nitter.cf/t.co/0I4eCVDeLu https://nitter.cf/t.co/M7JUu05A4N

New York, NY
Joined December 2018
Photo by Ameesh Makadia (@kiamada)Photo by Ameesh Makadia (@kiamada)Photo by Ameesh Makadia (@kiamada)Photo by Ameesh Makadia (@kiamada)Photo by Ameesh Makadia (@kiamada)Photo by Ameesh Makadia (@kiamada)
Ameesh Makadia retweeted
I am very proud to be part of this work led by @sudoRicheek and Pratik Chaudhari. In our new Science Robotics paper, we introduce F^3, Fast Feature Fields, moving beyond conventional optical-flow representations toward predictive event-based vision. science.org/doi/10.1126/scir…
2
4
1
63
2,722
Ameesh Makadia retweeted
I’m particularly appreciative of the support I’ve gotten from @CorinnaCortes, Katherine Chou, @ahfdc, @StephenWrage, Reuben Brigety, and more recently, my pre-doctoral scientific advisors, @kiamada and @WonderMicky.
1
1
1
196
Ameesh Makadia retweeted
We are hiring! This is an exciting space! Apply to us if you are interested!
📢 Google's Project Starline is looking for Student Researchers! Our team seeks students interested in real-time, high-realism human 3D modeling, relighting, materials reconstruction, novel view synthesis, diffusion models, transformers, and more. 🧵Look below for details!
1
5
35
6,167
⁦@TacoCohen⁩ ‘s first equivariant paper got me into this wonderful journey of symmetry. Here, at the very place where he received the Best Paper award for Spherical Networks in 2018!
1
1
57
2,937
🎊🎊🎊 congrats to @DavidCharatan @sizhe_lester_li and @vincesitzmann (We won one of the honorable mentions for best paper award at #CVPR2024)
📢📢📢 introducing 𝐩𝐢𝐱𝐞𝐥𝐒𝐩𝐥𝐚𝐭: feed-forward Gaussian splats from image pairs! pixelNeRF + 3D Gaussian Splatting == davidcharatan.com/pixelsplat Led by @DavidCharatan and @sizhe_lester_li, collaboration with @vincesitzmann
5
6
1
100
8,576
This was an amazing presentation by @erikjbekkers on equivariant neural fields and neural ideograms at the Equivision Workshop. I want to go and read all his 2024 papers now!
Looking forward to this! I'll talk about Neural Ideograms and Geometry-Grounded Representation Learning ... and cats and dogs and owls! Thank you @KostasPenn @CongyueD and co for organizing this! Excited to be part of the program!
2
6
36
6,246
Ameesh Makadia retweeted
At #CVPR2024, I will give a talk about "Geometric Deep Learning for Weather" at the Equivariant Vision workshop Tue 2pm equivision.github.io, and I'll present a poster on Single Mesh Diffusion Wed 5pm single-mesh-diffusion.github… w/ @twmitchel and @kiamada. Hope to see you there!
7
20
3,013
Ameesh Makadia retweeted
Giving a short talk today at the C3DV workshop today at CVPR around 2:20 PM. Will be discussing our main conference paper “Single Mesh Diffusion with Field Latents for Texture Generation”. 1/2
1
1
1
5
2,881
Ameesh Makadia retweeted
Come stopping by our EquiVision workshop tomorrow at Summit 321 with the exciting talks!
Our Equivariant Vision workshop features five great speakers @erikjbekkers @HaggaiMaron @ninamiolane @_machc, and Leo Guibas, spotlight talks, posters, and a tutorial prepared for the vision audience. Come tomorrow, Tuesday, at 8:30am in Summit 321! Thank you @CongyueD for leading the organization! equivision.github.io/index.h…
8
29
9,141
Our Equivariant Vision workshop features five great speakers @erikjbekkers @HaggaiMaron @ninamiolane @_machc, and Leo Guibas, spotlight talks, posters, and a tutorial prepared for the vision audience. Come tomorrow, Tuesday, at 8:30am in Summit 321! Thank you @CongyueD for leading the organization! equivision.github.io/index.h…
15
7
65
35,175
An image reconstructive representation learning loss that keeps scaling !!! You know how MAE does not benefit well from XLarge data. Well, if you borrow lessons from autoregressive language modeling, you can learn from Billion images and get 84% on IN1K. W/ Apple ML colleagues.
Excited to share AIM 🎯 - a set of large-scale vision models pre-trained solely using an autoregressive objective. We share the code & checkpoints of models up to 7B params, pre-trained for 1.2T patches (5B images) achieving 84% on ImageNet with a frozen trunk. (1/n) 🧵
2
13
1,802
Would you like to know how to define and realize an equivariant convolution and attention on a light field / feature field? Come to listen to @xu_yinshua86846 and @JiahuiLei1998 presenting our spotlight at 10:45am at poster#309 @NeurIPSConf
1
7
55
4,772
Ameesh Makadia retweeted
The first major WeatherBench 2 update is now live, including: ➕ New models: (pseudo-)operational Pangu and GraphCast, FuXi, SphericalCNN and NeuralGCM ➕ Improved scorecards (incl. a probabilistic one) ➕ More comprehensive ERA5 and IFS ENS data sites.research.google/weathe…
6
23
131
16,706
🌟FisherRF introduces a novel approach for view selection & uncertainty in 3D Gaussian Splatting & NeRFs. Fisher information can be computed without altering model architecture, and it is as cheap as back-propagation! 🚀More details: jiangwenpl.github.io/FisherR…
2
23
2
167
23,974
#CVPR2024 Such a great effort by my wonderful students. Excellent finish. Good luck to all of you. What a great feeling, 31 years of CVPR deadlines :-)
2
6
1
180
32,059
Ameesh Makadia retweeted
CVPR 1999 Best Paper Award Robust Hierarchical Algorithm for Constructing a Mosaic from Images of the Curved Human Retina A. Can, C. V. Stewart, B. Roysam #TBThursday
1
10
5,641
We proudly present our 524 page book on equivariant convolutional networks. Coauthored by Patrick Forré, @erikverlinde and @wellingmax. maurice-weiler.gitlab.io/#cn… [1/N]
27
241
23
1,119
161,603
Ameesh Makadia retweeted
Our blog post on scaling spherical CNNs for scientific applications was just published, check it out!
Applying computer vision models designed for planar images to data projected on spherical surfaces is challenging. Here we present an open-source library in JAX to solve the challenges of rotation and regular sampling for state-of-the-art performance → goo.gle/46z3vD7
1
5
30
4,156
Fun with spheres! cc @TacoCohen
Applying computer vision models designed for planar images to data projected on spherical surfaces is challenging. Here we present an open-source library in JAX to solve the challenges of rotation and regular sampling for state-of-the-art performance → goo.gle/46z3vD7
1
2
20
5,717
Ameesh Makadia retweeted
Some well-rounded results: @GoogleResearch work shows that deep learning on a sphere -- instead of flat space -- is superior for things like prediction of weather & molecular properties. Consider spherical surfaces (much better than pretending the world is flat!). See JAX code!
Applying computer vision models designed for planar images to data projected on spherical surfaces is challenging. Here we present an open-source library in JAX to solve the challenges of rotation and regular sampling for state-of-the-art performance → goo.gle/46z3vD7
11
44
1
362
102,207