Research Scientist, Google Research, NYC. https://teapawt.org/t.co/0I4eCVDeLu https://teapawt.org/t.co/M7JUu05A4N
New York, NY
Joined December 2018
- Tweets81
- Following220
- Followers443
- Likes257
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…
If you're at ICML this week, stop by and chat with @_machc to learn about designing noise schedules for diffusion (Wed, 2:30PM, Hall A)
Introducing "Spectrally-Guided Diffusion Noise Schedules", accepted to #ICML2026! With @kiamada.
We propose noise schedules that follow the power spectrum of each image, improving pixel diffusion quality and requiring fewer denoising steps.
At test time, we conditionally sample the spectrum before generating the image.
Denoising is conditioned on the spectrum, which allows manipulating properties like the amount of details, as the animations show.
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.
Ameesh Makadia retweeted
We are hiring! This is an exciting space! Apply to us if you are interested!
Rethinking image representations for autoregressive generation! Our new Spectral Image Tokenizer works in the image spectrum, where the coarse-to-fine representation has a more natural sequential interpretation
Our new paper, "Spectral Image Tokenizer", is on arXiv! We train a tokenizer on DWT coefficients
that enables autoregressive coarse-to-fine image generation, w/ applications to multiscale text-to-image, and text-guided editing.
w/ @kiamada, @msuhail153 arxiv.org/abs/2412.09607
Ameesh Makadia retweeted
@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!
Ameesh Makadia retweeted
🎊🎊🎊 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
Ameesh Makadia retweeted
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!
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!
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
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…
Ameesh Makadia retweeted
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…
Generate high quality textures with single mesh LDMs!
#CVPR2024
Our *intrinsic* 3D diffusion models, trained on a single mesh, can generate texture variations, perform inpainting, and even transfer textures to different shapes.
single-mesh-diffusion.github…
w/@twmitchel & @_machc
Ameesh Makadia retweeted
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.
Ameesh Makadia retweeted
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
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…
Ameesh Makadia retweeted
🌟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…
Ameesh Makadia retweeted
#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 :-)
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
Ameesh Makadia retweeted
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]
