32 citations · 128 across the 20 of their papers we have counts for
19 papers · 1 filter
Spectrally-Guided Diffusion Noise Schedules
Carlos Esteves, Ameesh Makadia
Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels…
Decomposing Private Image Generation via Coarse-to-Fine Wavelet Modeling
Jasmine Bayrooti, Weiwei Kong, Natalia Ponomareva +3
Generative models trained on sensitive image datasets risk memorizing and reproducing individual training examples, making strong privacy guarantees essential. While differential p…
Spectral Image Tokenizer
Carlos Esteves, Mohammed Suhail, Ameesh Makadia
Image tokenizers map images to sequences of discrete tokens, and are a crucial component of autoregressive transformer-based image generation. The tokens are typically associated w…
Factorized Video Autoencoders for Efficient Generative Modelling
Mohammed Suhail, Carlos Esteves, Leonid Sigal +1
Latent variable generative models have emerged as powerful tools for generative tasks including image and video synthesis. These models are enabled by pretrained autoencoders that…
Single Mesh Diffusion Models with Field Latents for Texture Generation
Thomas W. Mitchel, Carlos Esteves, Ameesh Makadia
We introduce a framework for intrinsic latent diffusion models operating directly on the surfaces of 3D shapes, with the goal of synthesizing high-quality textures. Our approach is…
Learning to Transform for Generalizable Instance-wise Invariance
Utkarsh Singhal, Carlos Esteves, Ameesh Makadia +1
Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or ha…
LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs
Zezhou Cheng, Carlos Esteves, Varun Jampani +3
A critical obstacle preventing NeRF models from being deployed broadly in the wild is their reliance on accurate camera poses. Consequently, there is growing interest in extending…
ASIC: Aligning Sparse in-the-wild Image Collections
Kamal Gupta, Varun Jampani, Carlos Esteves +4
We present a method for joint alignment of sparse in-the-wild image collections of an object category. Most prior works assume either ground-truth keypoint annotations or a large d…
Generalizable Patch-Based Neural Rendering
Mohammed Suhail, Carlos Esteves, Leonid Sigal +1
Neural rendering has received tremendous attention since the advent of Neural Radiance Fields (NeRF), and has pushed the state-of-the-art on novel-view synthesis considerably. The…
Light Field Neural Rendering
Mohammed Suhail, Carlos Esteves, Leonid Sigal +1
Classical light field rendering for novel view synthesis can accurately reproduce view-dependent effects such as reflection, refraction, and translucency, but requires a dense view…
Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold
Kieran Murphy, Carlos Esteves, Varun Jampani +2
Single image pose estimation is a fundamental problem in many vision and robotics tasks, and existing deep learning approaches suffer by not completely modeling and handling: i) un…
Learning Equivariant Representations
Carlos Esteves
State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolu…
An Analysis of SVD for Deep Rotation Estimation
Jake Levinson, Carlos Esteves, Kefan Chen +4
Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto or . These tools have long been used for a…
Spin-Weighted Spherical CNNs
Carlos Esteves, Ameesh Makadia, Kostas Daniilidis
Learning equivariant representations is a promising way to reduce sample and model complexity and improve the generalization performance of deep neural networks. The spherical CNNs…
Equivariant Multi-View Networks
Carlos Esteves, Yinshuang Xu, Christine Allen-Blanchette +1
Several popular approaches to 3D vision tasks process multiple views of the input independently with deep neural networks pre-trained on natural images, achieving view permutation…
Cross-Domain 3D Equivariant Image Embeddings
Carlos Esteves, Avneesh Sud, Zhengyi Luo +2
Spherical convolutional networks have been introduced recently as tools to learn powerful feature representations of 3D shapes. Spherical CNNs are equivariant to 3D rotations makin…
Labeling Panoramas with Spherical Hourglass Networks
Carlos Esteves, Kostas Daniilidis, Ameesh Makadia
With the recent proliferation of consumer-grade 360° cameras, it is worth revisiting visual perception challenges with spherical cameras given the potential benefit of their global…
Learning SO(3) Equivariant Representations with Spherical CNNs
Carlos Esteves, Christine Allen-Blanchette, Ameesh Makadia +1
We address the problem of 3D rotation equivariance in convolutional neural networks. 3D rotations have been a challenging nuisance in 3D classification tasks requiring higher capac…
Polar Transformer Networks
Carlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou +1
Convolutional neural networks (CNNs) are inherently equivariant to translation. Efforts to embed other forms of equivariance have concentrated solely on rotation. We expand the not…