We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conducts sensitivity analysis on hierarchical 3D image segmentation, and the other two visualize network activations on a spatial map. Visual chec…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “3D visualization”
3D RadViz improves 3D data visualization of multidimensional datasets.
problem Tackles the challenge of visualizing multidimensional datasets in 3D.
method Develops RadViz3D, a 3D radial visualization tool with uniform anchor points.
result Improves the display of multidimensional datasets, especially for uncorrelated variables.
3D filament plots visualize curves in datasets, avoiding visual clutter.
problem Visualizing high-dimensional data relationships in scatterplots of points.
method Construct 3D filament plots using linear isometries and Frenet-Serret systems.
result 3D filament plots preserve Euclidean distances and avoid visual clutter.
Build Boy's Surfacemath.HO
Easy-to-assemble 3D model of Boy's surface.
problem Visualizing Boy's surface in 3D.
method Printable card stock model kit.
result Accessible 3D representation of Boy's surface.
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…
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
problem Challenges in data efficiency, obstacle avoidance, and generalization in 3D visual navigation.
method Incorporates attention on 3D spatial relationships and a target skill extension module into DRL framework.
result Significantly improves navigation performance and generalization across targets and scenes.
The paper explores squircles and their 3D applications.
problem None explicitly stated; focuses on squircle equations and 3D surfaces.
method Examined and discussed squircle equations, then developed 3D surfaces based on these shapes.
result Developed 3D surfaces based on squircle equations.
Researchers classify and visualize 5-cube cubical surfaces.
problem Classifying and visualizing surfaces in a 5-dimensional cube.
method Exhaustive search, classification by genus and demigenus, 3D visualization, reinforcement learning for optimization.
result 2690 connected closed cubical surfaces in the 5-cube, visualized and optimized for 3D printing.
This note generalizes the visual angle to convex sets in 3D space.
problem Analyzing geometric properties of convex sets in 3D space.
method Generalizing the visual angle to convex sets in Euclidean space and expressing geometric quantities in terms of integrals of functions related to the solid angle.
result Invariant quantities of the original convex set can be expressed by integrals of functions related to the solid angle.
We solve 6-DoF localisation and 3D reconstruction using deep state-space models.
problem 6-DoF localisation and dense 3D reconstruction in spatial environments.
method Approximate Bayesian inference in a deep state-space model combining learning and domain knowledge.
result Near state-of-the-art performance on UAV flight data.
Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new generative model, Visual Object Networks (VON), synthesizing natural images of o…
Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of regularization, in this paper, we investigate the usage of non-convex regularizations in this problem. Our contribution consists of three parts. First, we propose the leaky capped …
Improved 3D ECG feature attributions for clinical interpretation.
problem Lack of interpretability in deep learning models for 12-lead ECG analysis.
method Cross-modal mapping of feature attributions from 12-lead ECG models onto CineECG 3D space.
result Mapped feature attributions yield higher Dice scores than standard 12-lead attributions.
Generates coherent 3D scenes from monocular videos without supervision.
problem Lack of 3D scene modeling in video generation models.
method Trains a model to generate 3D scenes with moving objects and a background from monocular videos.
result Trained model generates coherent 3D scenes with multiple moving objects and a background.
We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an implicit representation of the environment at a higher, more abstract level. We propose to use a generative approach based on Generative Query N…
AR app visualizes Quranic Surah al-Fil for Islamic education.
problem Lack of interactive and context-rich learning materials for Quranic studies.
method Research and development approach, including data collection, user requirement analysis, interface design, 3D asset creation, and integration of AR technology.
result AR application achieved high accuracy and user satisfaction, enhancing learner engagement and understanding.
Agent learns to navigate uncertain 3D maps using a hybrid planner.
problem Planning in 3D environments with uncertain topological maps.
method Hierarchical strategy combining graph planner and local policy, data-driven learning with neural network.
result Machine learning can overcome missing information in probabilistic topological maps.
This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized for a downstream task. We demonstrate this framework on 3D pose estimation by pro…
IANN visualizes all input variables effects simultaneously.
problem Inability to visualize all input variables effects simultaneously in black-box functions.
method Interpretable Architecture Neural Network (IANN) approach.
result Visualization of all input variables effects directly and simultaneously.
We present a test platform for visual in-cabin scene analysis and occupant monitoring functions. The test platform is based on a driving simulator developed at the DFKI, consisting of a realistic in-cabin mock-up and a wide-angle projection system for a realistic driving experience. The platform has been equipped with …
New dataset tests mental rotation from single images, improving model understanding of 3D scenes.
problem Understanding how a scene looks from a different viewpoint using a single image.
method Created CLEVR-MRT dataset, explored neural architectures for volumetric scene representations.
result Demonstrated the effectiveness of volumetric representations in answering mental rotation questions.
Study on bending knots and energy changes in 3D space.
problem Understanding energy changes in knots under small deformations.
method Analyzes infinitesimal bending of knots and energy changes using Willmore and Mobius energies.
result Changes in energy under small deformations of knots have been quantified.
Moduli spaces of planar polygonal linkages admit a cell structure which can be realized as a surgery on the permutohedron. We present a 3D visualization of the result of the surgery for all types of non-degenerate pentagonal linkages.
BPI models 2D patterns on multiple planes and 3D scene from a single image.
problem Understanding and editing images with multiple 2D planes and 3D scene from a single image.
method Box Program Induction (BPI) with neural networks and search-based algorithm.
result Holistic, structured scene representation enables 3D-aware image editing.
Large prospective epidemiological studies acquire cardiovascular magnetic resonance (CMR) images for pre-symptomatic populations and follow these over time. To support this approach, fully automatic large-scale 3D analysis is essential. In this work, we propose a novel deep neural network using both CMR images and pati…
Surfaces in The Tesseractmath.GT
Researchers visualize all surfaces from tesseract faces.
problem Visualizing all surfaces from tesseract faces.
method Generated 3D models of all closed surfaces and exhibited the Möbius strip.
result Generated and visualized all surfaces from tesseract faces.
Noise2Filter: fast, self-supervised learning and real-time reconstruction for 3D Computed Tomographyeess.IV
Noise2Filter improves 3D tomography reconstruction efficiency and accuracy.
problem Efficiently reconstructing 3D tomographic images in real-time with limited data.
method Self-supervised learning and a learned filter method.
result Noise2Filter achieves real-time reconstruction with limited loss of accuracy.
Deep network learns Obstacle Tower challenge without human demonstrations.
problem Master procedurally generated levels that get progressively harder.
method Deep Reinforcement Learning with a simple feed-forward network.
result Performed competitively in a reinforcement learning competition.
In this work, we introduce the Global Planar Convolution module as a building-block for fully-convolutional networks that aggregates global information and, therefore, enhances the context perception capabilities of segmentation networks in the context of brain tumor segmentation. We implement two baseline architecture…
Chest radiographs are commonly performed low-cost exams for screening and diagnosis. However, radiographs are 2D representations of 3D structures causing considerable clutter impeding visual inspection and automated image analysis. Here, we propose a Fully Convolutional Network to suppress, for a specific task, undesir…
Mapper-GIN: Lightweight Structural Graph Abstraction for Corrupted 3D Point Cloud Classificationcs.CV
Mapper-GIN simplifies 3D point cloud classification with lightweight structure.
problem Robust 3D point cloud classification under corruption.
method Mapper algorithm for structural decomposition, GIN for graph classification.
result Mapper-GIN achieves competitive accuracy with minimal parameters.
Protein-ligand scoring is an important step in a structure-based drug design pipeline. Selecting a correct binding pose and predicting the binding affinity of a protein-ligand complex enables effective virtual screening. Machine learning techniques can make use of the increasing amounts of structural data that are beco…
In this work we simulate null geodesics for the Bonnor massive dipole metric by implementing a symbolic-numerical algorithm in Sage and Python. This program is also capable of visualizing in 3D, in principle, the geodesics for any given metric. Geodesics are launched from a common point, collectively forming a cone of …
The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape represe…
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learnin…
Explains a 2D color exchange invariant correspondence to 3D linking numbers.
problem Understanding color exchange invariants in 2D dynamics and their 3D geometric interpretation.
method Visualizes invariants as linking of lines on a special surface with Arf-Kervaire invariant one, and interprets it as an obstruction to continuous transformation.
result Interprets a 2D color exchange invariant as a 3D linking number, providing a topological explanation.
For applications in computing, Bezier curves are pervasive and are defined by a piecewise linear curve L which is embedded in R^3 and yields a smooth polynomial curve C embedded in R^3. It is of interest to understand when L and C have the same embeddings. One class of counterexamples is shown for L being unknotted, wh…
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state …
The paper proposes a method to learn 3D object pose manifolds using GANs and elasticae.
problem Learning image manifolds of 3D objects with limited data.
method Geom-SGAN and elasticae for geometry-preserving image interpolation.
result The method outperforms state-of-the-art GANs and VAEs in learning rotation paths.
In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding space between the visual and textual manifolds. On the visual side, we used activity videos and a state-of-the-art 3D convolutional action recog…
Topology-GS improves 3D GS for better structural and feature integrity.
problem Compromised pixel-level and feature-level integrity in 3D GS.
method Incorporates Local Persistent Voronoi Interpolation (LPVI) and PersLoss based on persistent homology.
result Topology-GS outperforms existing methods in PSNR, SSIM, and LPIPS metrics.
We explore visual representations of tilings corresponding to Schläfli symbols. In three dimensions, we call these tilings "honeycombs". Schläfli symbols encode, in a very efficient way, regular tilings of spherical, euclidean and hyperbolic spaces in all dimensions. In three dimensions, there are only a finite number …
In this work we propose a model that can manipulate individual visual attributes of objects in a real scene using examples of how respective attribute manipulations affect the output of a simulation. As an example, we train our model to manipulate the expression of a human face using nonphotorealistic 3D renders of a f…
NEURO-DRAM: a 3D recurrent visual attention model for interpretable neuroimaging classificationcs.LG
Deep learning is attracting significant interest in the neuroimaging community as a means to diagnose psychiatric and neurological disorders from structural magnetic resonance images. However, there is a tendency amongst researchers to adopt architectures optimized for traditional computer vision tasks, rather than des…
Study of loxodromes on twisted surfaces in 3D space.
problem Characterizing loxodromes on surfaces with varying curvature.
method Analysis of loxodromes on twisted surfaces in Euclidean 3-space.
result Construction of examples to visualize loxodromes on twisted surfaces.
3D U-Net improves kidney and tumor segmentation from CT scans.
problem Manual segmentation by clinicians is laborious and error-prone.
method Multi-scale supervised 3D U-Net with deep supervision and post-processing.
result MSS U-Net achieves high Dice coefficients (0.969 for kidney, 0.805 for tumor) on KiTS19 dataset.
We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric capsule represents a visual entity, such as an object or a part, and consists of two components: a pose and a feature. The pose encodes whe…
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid …