Related papers: SN-Engine, a Scale-free Geometric Modelling Enviro…

In this paper, we introduce SDM-UniPS, a groundbreaking Scalable, Detailed, Mask-free, and Universal Photometric Stereo network. Our approach can recover astonishingly intricate surface normal maps, rivaling the quality of 3D scanners, even…

The goal of this note is to give a systematic method of constructing zero-free regions for the permanent in the sense of A. Barvinok, i.e. regions in the complex plane such that the permanent of a square matrix of any size with entries from…

Nested space-filling designs are nested designs with attractive low-dimensional stratification. Such designs are gaining popularity in statistics, applied mathematics and engineering. Their applications include multi-fidelity computer…

Autoencoders have emerged as powerful models for visualization and dimensionality reduction based on the fundamental assumption that high-dimensional data is generated from a low-dimensional manifold. A critical challenge in autoencoder…

We present a scalable Gaussian process model for identifying and characterizing smooth multidimensional changepoints, and automatically learning changes in expressive covariance structure. We use Random Kitchen Sink features to flexibly…

In recent years, the recognition of free-hand sketches has remained a popular task. However, in some special fields such as the military field, free-hand sketches are difficult to sample on a large scale. Common data augmentation and image…

In this work, we present an integrated geometric framework: "deep- cut" that enables for the first time a user to geometrically and algorithmically cut, tear and drill the surface of a skinned model without prior constraints, layered on top…

We present a novel methodology based on geometric approach to simulate magnification lens effects. Our aim is to promote new applications of powerful geometric modeling techniques in visual computing. Conventional image…

We propose a new probabilistic framework that allows mobile robots to autonomously learn deep, generative models of their environments that span multiple levels of abstraction. Unlike traditional approaches that combine engineered models…

In this work, we present a workspace-based planning framework, which though using redundant workspace key-points to represent robot states, can take advantage of the interpretable geometric information to derive good quality collision-free…

In the field of 3D content generation, single image scene reconstruction methods still struggle to simultaneously ensure the quality of individual assets and the coherence of the overall scene in complex environments, while texture editing…

General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped. We present an algorithm which…

Simulation has become the evaluation method of choice for many areas of distributing computing research. However, most existing simulation packages have several limitations on the size and complexity of the system being modeled. Fine…

We propose a new scalable algorithm for holistic linear regression building on Bertsimas & King (2016). Specifically, we develop new theory to model significance and multicollinearity as lazy constraints rather than checking the conditions…

Due to the tremendous cost of seismic data acquisition, methods have been developed to reduce the amount of data acquired by designing optimal missing trace reconstruction algorithms. These technologies are designed to record as little data…

Object rearrangement is pivotal in robotic-environment interactions, representing a significant capability in embodied AI. In this paper, we present SG-Bot, a novel rearrangement framework that utilizes a coarse-to-fine scheme with a scene…

Neuromorphic computing and, in particular, spiking neural networks (SNNs) have become an attractive alternative to deep neural networks for a broad range of signal processing applications, processing static and/or temporal inputs from…

In this paper, we present an algorithm to automatically detect meaningful modes in a histogram. The proposed method is based on the behavior of local minima in a scale-space representation. We show that the detection of such meaningful…

Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-fidelity training data. Pre-training on abundant off-the-shelf geometries offers a natural…

We introduce a quantile-adaptive framework for nonlinear variable screening with high-dimensional heterogeneous data. This framework has two distinctive features: (1) it allows the set of active variables to vary across quantiles, thus…