Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,982 papers · 148 categories

Trend · papers per month

14284256 · Oct 201919922001200920172026
48 results for 3D motion

New framework predicts diverse, contextually plausible 3D human motions.

problem Predicting multiple plausible future 3D poses given observed poses.
method Developed a new variational framework that conditions latent variable on past observation to encourage relevant information.
result Our approach generates motions of higher quality and preserves contextual information.

Selective relevance method improves motion explainability in 3D activity recognition models.

problem Models do not appropriately factor motion information into their decisions.
method Selective relevance method to adapt 2D explanation techniques for 3D inputs.
result Improves selectivity of motion explanations, revealing model's spatial bias.

DMGNN predicts 3D human motions using adaptive multiscale graphs.

problem Predicting 3D skeleton-based human motions accurately.
method Dynamic multiscale graph neural networks (DMGNN) with adaptive multiscale graphs and MGCU.
result DMGNN outperforms state-of-the-art methods in short and long-term predictions.

Paper presents a method for recognizing human actions using GLAC features from motion and static images.

problem Action recognition in 3D depth videos.
method 3D Motion Trail Model (3DMTM) for MHIs and SHIs, GLAC features extraction, l2-regularized Collaborative Representation Classifier (l2-CRC) for classification.
result The method outperforms other approaches in recognizing human actions.

V-SysId identifies keypoints and 3D system from unlabeled videos.

problem Identifying keypoints and 3D system from unlabeled videos.
method Alternates between parameter estimation and extrinsic camera calibration, using motion equations as weak supervision.
result Utility of the approach demonstrated across various settings.

There is a remarkable and canonical problem in 3D geometry and topology: To understand existing models of 3D fluid motion or to create new ones that may be useful. We discuss from an algebraic viewpoint the PDE called Euler's equation for incompressible frictionless fluid motion. In part I we define a "finite dimension…

2010-10-13abs ↗pdf ↗

Study null curves and their motion in 3D flat space-time, leading to integrable hierarchies.

problem Understanding null curves and their motion in 3D flat space-time.
method Analyzing the motion of null curves and their surfaces, deriving integrability conditions and hierarchies.
result Obtained one- and two-soliton surfaces associated with the MKdV equation, showing singularities in finite time.

Paper proves minimizing movements match smooth droplet flow in 3D.

problem Consistency of minimizing movements with smooth mean curvature flow.
method Proved minimizing movements coincide with smooth droplet flow.
result Minimizing movements and smooth mean curvature flow are consistent in 3D.

Estimation of facial expressions, as spatio-temporal processes, can take advantage of kernel methods if one considers facial landmark positions and their motion in 3D space. We applied support vector classification with kernels derived from dynamic time-warping similarity measures. We achieved over 99% accuracy - measu…

2013-06-08abs ↗pdf ↗

Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars. Existing motion planning methods become ineffective as their computational complexity increases exponentially with the dimensionality of the motion planning problem. To address this issue…

2018-06-14abs ↗pdf ↗

The field of multiple view geometry has seen tremendous progress in reconstruction and calibration due to methods for extracting reliable point features and key developments in projective geometry. Point features, however, are not available in certain applications and result in unstructured point cloud reconstructions.…

2016-04-27abs ↗pdf ↗

Study on curve shortening flow in 3D space curves, showing convexity preservation and avoidance principle.

problem Analyzing the behavior of space curves under curve shortening flow in R3\mathbb{R}^3.
method Analysis of properties of space curves evolved by the curve shortening flow, including convexity preservation and avoidance principle.
result Orthogonal projections of space curves remain convex, and the Avoidance principle is shown for spherical curves.

This work improves motion planning for quadcopters by learning and reasoning about controller performance.

problem Improving motion planning for quadcopters with safety margins and execution reliability.
method Introspective learning and reasoning to correct execution bias and improve collision checking.
result Substantial reduction in safety margins for motion actions, leading to safer execution.

Proposes local coordinate frames for improving model performance in complex dynamical systems.

problem Improving model performance in complex, non-linear, and time-dependent dynamical systems.
method Introduces roto-translation invariant local coordinate frames for geometric graphs.
result The approach outperforms state-of-the-art models in various complex scenarios.

The paper analyzes self-similar solutions for mean curvature flow in 3D.

problem Analyzing self-similar solutions for mean curvature flow in R3\mathbb{R}^{3}.
method Analysis of self-similar solutions for surfaces of revolution, ruled surfaces, and cylindrical surfaces under homothetic helicoidal motions.
result Characterization and explicit families of exact solutions for cylindrical surfaces.

RNN operators solve Newton's equations with large timesteps for molecular dynamics.

problem Solving Newton's equations of motion with large timesteps for molecular dynamics simulations.
method Recurrent Neural Networks (RNN) operators to solve Newton's equations using past trajectory data.
result Significant speedup in molecular dynamics simulations with timesteps up to 4000 times larger.

By studying the group of rigid motions, PSH(1)PSH(1), in the 3D-Heisenberg group H1H_1, we define the density and the measure for the sets of horizontal lines. We show that the volume of a convex domain DH1D\subset H_1 is equal to the integral of length of chord over all horizontal lines intersecting DD. As the classical r…

2016-09-10abs ↗pdf ↗

High-dimensional ConvNets detect patterns in 32+ dimensions for geometric registration.

problem Detecting geometric patterns in high-dimensional spaces.
method High-dimensional convolutional networks applied to geometric registration problems.
result High-dimensional ConvNets outperform global pooling approaches in 3D registration and image correspondence.

AniDS improves molecular force field modeling by learning anisotropic noise.

problem Molecular force field modeling suffers from oversimplified assumptions about atomic motions.
method AniDS introduces anisotropic noise generation for better modeling of directional and structural variability.
result AniDS outperforms existing methods on benchmarks, achieving significant improvements in force prediction accuracy.

Y-GAN uses multi-camera data to estimate depth maps without expensive hardware.

problem Depth perception for autonomous systems requires accurate 3D spatial information.
method Proposes Y-GAN, a deep convolutional generative adversarial network.
result Y-GAN estimates depth maps from multi-camera stereo images without ground truth data.

Real-time drowsiness detection on mobile phones reduces road trauma.

problem Driver drowsiness increases crash risk and road trauma.
method Depthwise separable 3D convolutions combined with early fusion of spatial and temporal information.
result Real-time drowsiness detection on mobile phones reduces road trauma.

FEAFA dataset annotates facial expressions with high detail.

problem Lack of detailed facial expression annotations in existing datasets.
method Manual annotation of 122 participants' facial expressions.
result FEAFA dataset provides detailed annotations for facial expressions.

Paper introduces a method for generating interlocutor-aware facial gestures in dyadic settings.

problem Generating appropriate non-verbal behavior for conversational agents in dyadic settings.
method Probabilistic method using multi-modal cues from the interlocutor to synthesize facial gestures.
result The model successfully leverages multi-modal input from the interlocutor to generate more appropriate behavior.

Paper introduces TAP-Vid, a benchmark for tracking any point in videos.

problem Tackles the problem of tracking arbitrary physical points on surfaces over longer video clips.
method Formalizes the problem as TAP, introduces TAP-Vid benchmark, uses crowdsourced pipeline with optical flow estimates, proposes TAP-Net model.
result TAP-Net outperforms all prior methods on TAP-Vid benchmark when trained on synthetic data.

Study of geodesics on SL(n) with Hilbert-Schmidt metric, revealing complex dynamics in higher dimensions.

problem Geodesics on SL(n) with Hilbert-Schmidt metric.
method Analysis of geodesics, use of Virial-identity-based criterion, study of explicit families of solutions, classification of geodesics.
result Complex dynamics in higher dimensions, existence of bounded geodesic motions in even dimensions, instability of swirling and shear flows in even dimensions.

Study characterizes bladder motion using dynamic MRI and statistical analysis.

problem Limited volume coverage in dynamic MRI sequences hinders 3D shape reconstruction.
method 3D dense velocity measurements, LDDMM framework, statistical characterization, mean curvature changes, surface deformation analysis.
result Stable shape descriptor for characterizing bladder surface dynamics.

This paper studies Sasakian quasi-Killing spinors on 3D Sasakian manifolds.

problem Characterizing Sasakian quasi-Killing spinors on 3D Sasakian manifolds.
method Detailed analysis and geometric properties of Sasakian quasi-Killing spinors.
result Almost all Sasakian quasi-Killing spinors solve the Einstein-Dirac system with a non-zero cosmological constant.

We address the problem of surface inpainting, which aims to fill in holes or missing regions on a Riemann surface based on its surface geometry. In practical situation, surfaces obtained from range scanners often have holes where the 3D models are incomplete. In order to analyze the 3D shapes effectively, restoring the…

2012-12-05abs ↗pdf ↗

A new diffusion model generates novel protein backbones without relying on pretrained networks.

problem Generating novel protein backbones without relying on pretrained networks.
method Developed a SE(3) invariant diffusion model on multiple frames, called FrameDiff.
result Generated designable protein monomers up to 500 amino acids without pretrained networks.