Carlos Esteves
I am a Research Scientist at Google Research, NYC. Please visit my website for more details and complete list of publications.
Research Areas
Authored Publications
Sort By
Preview abstract
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 with spatial locations in the input image, arranged in raster scan order, which is not ideal for autoregressive modeling. In this paper, we propose to tokenize the image spectrum instead, obtained from a discrete wavelet transform (DWT), such that the sequence of tokens represents the image in a coarse-to-fine fashion. Our tokenizer brings several advantages: 1) it leverages that natural images are more compressible at high frequencies, 2) it can take and reconstruct images of different resolutions without retraining, 3) it improves the conditioning for next-token prediction -- instead of conditioning on a partial line-by-line reconstruction of the image, it takes a coarse reconstruction of the full image, 4) it enables partial decoding where the first few generated tokens can reconstruct a coarse version of the image, 5) it enables autoregressive models to be used for image upsampling. We evaluate the tokenizer reconstruction metrics as well as multiscale image generation, text-guided image upsampling and editing.
View details
Single Mesh Diffusion Models with Field Latents for Texture Generation
Thomas Mitchel
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (2024)
Preview abstract
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 underpinned by two contributions: field latents, a latent representation encoding textures as discrete vector fields on the mesh vertices, and field latent diffusion models, which learn to denoise a diffusion process in the learned latent space on the surface. We consider a single-textured-mesh paradigm, where our models are trained to generate variations of a given texture on a mesh. We show the synthesized textures are of demonstrably superior fidelity compared those from existing single-3D-asset generative models. Our models can also be adapted for user-controlled editing tasks such as inpainting and label-guided generation. The efficacy of our approach is due in part to the equivariance of our proposed framework under isometries, allowing our models to seamlessly reproduce details across locally similar regions and opening the door to a notion of generative texture transfer.
View details
Learning to Transform for Generalizable Instance-wise Invariance
Utkarsh Singhal
Stella Yu
International Conference on Compute Vision (2023)
Preview abstract
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 hard-coding invariances into the architecture. However, too much or too little invariance can hurt, and the correct amount is unknown a priori and dependent on the instance. Ideally, the appropriate invariance would be learned from data and inferred at test-time.
We treat invariance as a prediction problem. Given any image, we use a normalizing flow to predict a distribution over transformations and average the predictions over them. Since this distribution only depends on the instance, we can align instances before classifying them and generalize invariance across classes. The same distribution can also be used to adapt to out-of-distribution poses. This normalizing flow is trained end-to-end and can learn a much larger range of transformations than Augerino and InstaAug. When used as data augmentation, our method shows accuracy and robustness gains on CIFAR 10, CIFAR10-LT, and TinyImageNet.
View details
ASIC: Aligning Sparse in-the-wild Image Collections
Kamal Gupta
Varun Jampani
Abhinav Shrivastava
Abhishek Kar
International Conference on Computer Vision (ICCV) (2023)
Preview abstract
We present a method for joint alignment of sparse in-thewild image collections of an object category. Most prior works assume either ground-truth keypoint annotations or a large dataset of images of a single object category. However, neither of the above assumptions hold true for the longtail of the objects present in the world. We present a selfsupervised technique that directly optimizes on a sparse collection of images of a particular object/object category to obtain consistent dense correspondences across the collection. We use pairwise nearest neighbors obtained from deep features of a pre-trained vision transformer (ViT) model as noisy and sparse keypoint matches and make them dense and accurate matches by optimizing a neural network that jointly maps the image collection into a learned canonical grid. Experiments on CUB and SPair-71k benchmarks demonstrate that our method can produce globally consistent and higher quality correspondences across the image collection when compared to existing self-supervised methods. Code and other material will be made available at https://kampta.github.io/asic.
View details
LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs
Zezhou Cheng
Varun Jampani
Abhishek Kar
Subhransu Maji
International Conference on Computer Vision (ICCV) (2023)
Preview abstract
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 NeRF models to jointly optimize camera poses and scene representation, which offers an alternative to offthe-shelf SfM pipelines which have well-understood failure modes. Existing approaches for unposed NeRF operate under limiting assumptions, such as a prior pose distribution or coarse pose initialization, making them less effective in a general setting. In this work, we propose a novel approach, LU-NeRF, that jointly estimates camera poses and neural radiance fields with relaxed assumptions on pose configuration. Our approach operates in a local-to-global manner, where we first optimize over local subsets of the data, dubbed “mini-scenes.” LU-NeRF estimates local pose and geometry for this challenging few-shot task. The mini-scene
poses are brought into a global reference frame through a robust pose synchronization step, where a final global optimization of pose and scene can be performed. We show our LU-NeRF pipeline outperforms prior attempts at unposed NeRF without making restrictive assumptions on the pose prior. This allows us to operate in the general SE(3) pose setting, unlike the baselines. Our results also indicate our model can be complementary to feature-based SfM
pipelines as it compares favorably to COLMAP on lowtexture and low-resolution images.
View details
Scaling Spherical CNNs
Jean-Jacques Slotine
International Conference on Machine Learning (ICML) (2023)
Preview abstract
Spherical CNNs generalize CNNs to functions on the sphere, by using spherical convolutions as the main linear operation. The most accurate and efficient way to compute spherical convolutions is in the spectral domain (via the convolution theorem), but this is still much more costly than the usual planar convolutions. For this reason, applications of spherical CNNs have so far been limited to small problems that can be approached with low model capacity. In this work, we show how spherical CNNs can be scaled for much larger problems. To achieve this, we made critical improvements including an implementation of core operations to exploit hardware accelerator characteristics, introducing novel variants of common model components, and showing how to construct application-specific input representations that exploit the properties of our model. Experiments show our larger spherical CNNs reach state-of-the-art on several targets of the QM9 molecular benchmark, which was previously dominated by equivariant graph neural networks, and achieve competitive performance on multiple weather forecasting tasks.
View details
Generalizable Patch-Based Neural Rendering
Mohammed Suhail
Leonid Sigal
European Conference on Computer Vision (2022) (to appear)
Preview abstract
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 recent focus has been on models
that overfit to a single scene, and the few attempts to learn models
that can synthesize novel views of unseen scenes mostly consist of
combining deep convolutional features with a NeRF-like model. We
propose a different paradigm, where no deep visual features and no
NeRF-like volume rendering are needed. Our method is capable of
predicting the color of a target ray in a novel scene directly, just
from a collection of patches sampled from the scene. We first leverage
epipolar geometry to extract patches along the epipolar lines of each
reference view. Each patch is linearly projected into a 1D feature
vector and a sequence of transformers process the collection. For
positional encoding, we parameterize rays as in a light field
representation, with the crucial difference that the coordinates are
canonicalized with respect to the target ray, which makes our method
independent of the reference frame and improves generalization. We
show that our approach outperforms the state-of-the-art on novel view
synthesis of unseen scenes even when being trained with considerably
less data than prior work. Our code is available at
https://mohammedsuhail.net/gen_patch_neural_rendering.
View details
Light Field Neural Rendering
Mohammed Suhail
Leonid Sigal
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)
Preview abstract
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 sampling of
the scene. Methods based on geometric reconstruction need only sparse
views, but cannot accurately model non-Lambertian effects. We
introduce a model that combines the strengths and mitigates the
limitations of these two directions. By operating on a
four-dimensional representation of the light field, our model learns
to represent view-dependent effects accurately. By enforcing geometric
constraints during training and inference, the scene geometry is
implicitly learned from a sparse set of views. Concretely, we
introduce a two-stage transformer-based model that first aggregates
features along epipolar lines, then aggregates features along
reference views to produce the color of a target ray. Our model
outperforms the state-of-the-art on multiple forward-facing and 360◦
datasets, with larger margins on scenes with severe view-dependent
variations. Code and results can be found at light-field-neural-
rendering.github.io.
View details
Preview abstract
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) uncertainty about the
predictions, and ii) symmetric objects with multiple (sometimes
infinite) correct poses. To this end, we introduce a method to
estimate arbitrary, non-parametric distributions on SO(3). Our key
idea is to represent the distributions implicitly, with a neural
network that estimates the probability given the input image and a
candidate pose. Grid sampling or gradient ascent can be used to find
the most likely pose, but it is also possible to evaluate the
probability at any pose, enabling reasoning about symmetries and
uncertainty. This is the most general way of representing
distributions on manifolds, and to showcase the rich expressive power,
we introduce a dataset of challenging symmetric and nearly-symmetric
objects. We require no supervision on pose uncertainty – the model
trains only with a single pose per example. Nonetheless, our implicit
model is highly expressive to handle complex distributions over 3D
poses, while still obtaining accurate pose estimation on standard
non-ambiguous environments, achieving state-of-the-art performance
on Pascal3D+ and ModelNet10-SO(3) benchmarks. Code, data, and
visualizations may be found at implicit-pdf.github.io.
View details
An Analysis of SVD for Deep Rotation Estimation
Jake Levinson
Arthur Chen
Angjoo Kanazawa
Afshin Rostamizadeh
Advances in Neural Information Processing Systems (NeurIPS) 2020
Preview abstract
Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto O(n) or SO(n). These tools have long been used for applications in computer vision, for example optimal 3D alignment problems solved by orthogonal Procrustes, rotation averaging, or Essential matrix decomposition. Despite its utility in different settings, SVD orthogonalization as a procedure for producing rotation matrices is typically overlooked in deep learning models, where the preferences tend toward classic representations like unit quaternions, Euler angles, and axis-angle, or more recently-introduced methods. Despite the importance of 3D rotations in computer vision and robotics, a single universally effective representation is still missing. Here, we explore the viability of SVD orthogonalization for 3D rotations in neural networks. We present a theoretical analysis of SVD as used for projection onto the rotation group. Our extensive quantitative analysis shows simply replacing existing representations with the SVD orthogonalization procedure obtains state of the art performance in many deep learning applications covering both supervised and unsupervised training.
View details
