arXiv research

We show that 3D gravity, in its pure connection formulation, admits a natural 6D interpretation. The 3D field equations for the connection are equivalent to 6D Hitchin equations for the Chern-Simons 3-form in the total space of the principal bundle over the 3-dimensional base. Turning this construction around one gets …

The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and the design of accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition…

Study bends 2D surfaces in 3D space using special equations.

For several classes of second order dispersionless PDEs, we show that the symbols of their formal linearizations define conformal structures which must be Einstein-Weyl in 3D (or self-dual in 4D) if and only if the PDE is integrable by the method of hydrodynamic reductions. This demonstrates that the integrability of t…

The paper classifies path structures on 3D Lie groups and reduces non-flat ones to Z/2Z-structures.

The paper explores the connection between 3d gravity and Chern-Simons theory using affine group connections.

CARV reduces compute cost for downstream pipelines using diffusion models.

RCLA reduces noise in topological data analysis, preserving essential structure.

Paper reduces false positives in lung nodule detection using deep learning on point clouds.

pyLOT library simplifies machine learning on 3D point clouds via linearized optimal transport.

We consider the optimal control problem for null curves in de Sitter 3-space defined by a functional which is linear in the curvature of the trajectory. We show how techniques based on the method of moving frames and exterior differential systems, coupled with the reduction procedure for systems with a Lie group of sym…

Convolutional Neural Networks (CNNs) require a large amount of annotated data to learn from, which is often difficult to obtain in the medical domain. In this paper we show that the sample complexity of CNNs can be significantly improved by using 3D roto-translation group convolutions (G-Convs) instead of the more conv…

A novel 3D shape registration method using spectral graph embedding and probabilistic matching.

We show that the smooth geometry of a hyperbolic 3-manifold emerges from a classical spin system defined on a 2d discrete lattice, and moreover show that the process of this "dimensional oxidation" is equivalent with the dimensional reduction of a supersymmetric gauge theory from 4d to 3d. More concretely, we propose a…

Topology optimization is computationally demanding that requires the assembly and solution to a finite element problem for each material distribution hypothesis. As a complementary alternative to the traditional physics-based topology optimization, we explore a data-driven approach that can quickly generate accurate so…

Bayesian framework optimizes 3D view selection for specific tasks.

A 3D flexible bin packing problem (3D-FBPP) arises from the process of warehouse packing in e-commerce. An online customer's order usually contains several items and needs to be packed as a whole before shipping. In particular, 5% of tens of millions of packages are using plastic wrapping as outer packaging every day, …

Study 4D steady gradient Ricci solitons reducing to 3D manifolds.

Paper proposes PCA-GMM for efficient superresolution of material images.

We study knots in 3d Chern-Simons theory with complex gauge group $SL(N,\mathbb{C})$, in the context of its relation with 3d $\mathcal{N}=2$ theory (the so-called 3d-3d correspondence). The defect has either co-dimension 2 or co-dimension 4 inside the 6d $(2,0)$ theory, which is compactified on a 3-manifold $\hat{M}$. …

Data assimilation for subsurface flow using latent diffusion models shows that ensemble Kalman methods may overestimate posterior uncertainty, while Monte Carlo sampling is more reliable.

Study of 3d-3d correspondence involving $q$-Weyl algebra and 3d-index.

Motivated by the idea of turbomachinery active subspace performance maps, this paper studies dimension reduction in turbomachinery 3D CFD simulations. First, we show that these subspaces exist across different blades---under the same parametrization---largely independent of their Mach number or Reynolds number. This is…

VCAE improves autoencoder quality on MNIST and CelebA.

3D dual field theories for Virasoro minimal models constructed using Seifert fiber spaces.

3D flying wings created for any angle asymptotic cones.

Proposes a new effective central charge for 3d N=2 theories.

Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…

Smooth 3D flows from non-smooth starting points.

3D Axial-Attention improves lung nodule classification accuracy.

3D steady gradient Ricci solitons are all O(2)-symmetric.

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…

Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks including 3D points generation, reconstruction, compression…

Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based on Asynchronous Advantage Actor-Critic (A3C) algorithm where the total input dimensionality is halv…

Graph Neural Networks improve 3D object detection in LiDAR point clouds.

The study connects knot complements to 3d theories via half-index calculations.

Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve inter-class discrimination efficiently. In this paper, we propose a two-faceted sol…

GCDM generates valid large 3D molecules and optimizes existing molecules.

Generates coherent 3D scenes from monocular videos without supervision.

The paper studies decay near singularities of 3d Yang-Mills-Higgs fields.

Researchers discover a new family of 3D solitons that are flying wings.

Defines a map connecting 3d-index and skein module.

PredPCA extracts key components for better time series prediction.

Study large N oscillations in 3D theories related to black hole physics.

Enhances 2D face recognition with 3D features using active illumination.

Early diagnosis, playing an important role in preventing progress and treating the Alzheimer\{'}s disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocamp…

Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.