DVAO predicts volumetric ambient occlusion for real-time volume rendering.
problem Predicting per-voxel ambient occlusion in volumetric data sets.
method Deep learning neural network that considers global information through transfer function.
result DVAO supports real-time volume interaction and generalizes to various modalities.
A new method for adversarial attacks using physical parameters like lighting and geometry.
problem Vulnerability of machine learning image classifiers to adversarial attacks.
method Directly perturbs physical parameters (lighting and geometry) instead of pixel colors, using a differentiable renderer.
result Proposes parametric norm-balls for evaluating adversarial attacks, enabling physically-based attacks.
Method tracks finger movements to render shapes on display devices.
problem Designing touchless user interfaces for electronic devices.
method Leap Motion controller tracks finger movements, analyzes trajectories, and uses HMM for gesture recognition.
result Method achieves 92.87% accuracy in rendering shapes on display devices.
FI-GNNs learn expressive node representations from sparse features.
problem Sparse and high-dimensional node features limit GNN performance.
method Plug-and-play GNN framework that highlights informative feature interactions.
result FI-GNNs learn highly expressive node representations on feature-sparse graphs.
VectorNet predicts car behavior using vectorized HD maps and agent dynamics.
problem Predicting behavior in multi-agent systems with self-driving cars.
method VectorNet uses hierarchical graph neural networks on vectorized representations of HD maps and agent trajectories.
result VectorNet achieves comparable or better performance than state-of-the-art methods while using fewer parameters and less computational power.
We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds---e.g. the characteristic silverlining and the "whiteness" …
StyleNeRF generates high-resolution images with 3D consistency and style control.
problem Generating high-resolution images with fine details and 3D consistency.
method Integrates NeRF into a style-based generator for efficient high-resolution image synthesis.
result Synthesizes high-resolution images at interactive rates with high 3D consistency and style control.
A model learns object representations for physical scene understanding without direct supervision.
problem Learning object-centric representations without direct supervision of object properties.
method Object-Oriented Prediction and Planning (O2P2) model that learns perception, physics interaction, and rendering functions.
result The model can predict physical interactions and build block towers more complex than those seen during training.
TensorWatch enables real-time interactive analysis of deep learning training.
problem Challenges in diagnosing and exploring deep learning models during training.
method Modeling inspection and diagnostic tasks as streams using a map-reduce paradigm.
result Real-time interactive queries on live deep learning training processes.
Modeling and learning turn-taking behaviors in multi-agent systems.
problem Modeling and predicting turn-taking behaviors in dynamic multi-agent systems.
method Individual behavior models (WFSTs) and multi-agent fusion model (logistic regression classifier).
result Accurately models and predicts turn-taking behaviors with high precision.
ORRB enables fast, customizable rendering of robotics environments.
problem Fast and customizable rendering of robotics environments.
method Based on Unity3d and MuJoCo, optimized for cloud deployment.
result Visual domain randomization for improved simulation.
Proposes MCCF to distinguish latent purchasing motivations in user-item interactions.
problem Difficulty in capturing fine-grained user preferences due to complex latent motivations.
method Introduces MCCF with decomposer and combiner modules to identify and recombine latent components.
result Significant performance gains and necessity of considering multiple components demonstrated.
DSRGAN learns independent structure and rendering without tuple supervision.
problem Learning disentangled representation for natural image generation without tuple supervision.
method Introducing an auxiliary domain with a common underlying-structure space, and designing a parallel generative network with a common Progressive Rendering Architecture.
result DSRGAN significantly outperforms state-of-the-art methods in disentanglability.
Safe exploration framework for IML algorithms.
problem Safe decision-making in IML without unsafe outcomes.
method Exploits Gaussian process prior to efficiently learn safe decisions.
result Outperforms other algorithms empirically.
Describes rendering scenes in Nil geometry.
problem None explicitly stated in the abstract.
method Expository account of rendering real-time scenes in Nil geometry.
result Interesting geometric phenomena observed.
Enhances neural rendering with geometry-aware attention.
problem Efficiently modeling complex 3D scenes.
method Introduces Epipolar Cross Attention (ECA) for non-local operations.
result Significant improvement in Generative Query Networks (GQN) performance.
Automates hair color digitization using imaging and deep learning.
problem Challenges in capturing and rendering realistic hair colors.
method Combines imaging, path-tracing, and self-supervised machine learning.
result Accurately captures and renders hair color with synthetic images.
Data visualization and interaction with large data sets is known to be essential and critical in many businesses today, and the same applies to research and teaching, in this case, when exploring large and complex mathematical objects. GAP is a computer algebra system for computational discrete algebra with an emphasis…
A neural scene representation framework enforcing 3D transformations.
problem Learning 3D scene representations from images without 3D supervision.
method Introducing a loss enforcing equivariance of the scene representation with 3D transformations.
result Real-time neural rendering with comparable results to models requiring minutes for inference.
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.
Efficiently searches for optimal neural architecture and hyperparameters.
problem Separate tuning of architecture and hyperparameters leads to suboptimal results.
method Combines Bayesian optimization and Hyperband for joint search.
result Joint search yields better results with fewer epochs.
Study examines synthetic images with reflecting materials for training object detectors.
problem Training object detectors on synthetic images containing reflecting materials.
method Investigated rendering approach, domain randomization, and training data amount.
result Synthetic images with reflecting materials improve object detector performance.
We create real-time geodesic rendering for non-isotropic geometries.
problem Challenging visualization of non-isotropic geometries.
method Novel methods for real-time native geodesic rendering.
result Methods can be applied to visualization, machine learning, and video games.
ROOTS learns to represent and render 3D scenes with object-centric models.
problem Learning to represent and render 3D scenes with object-centric compositionality.
method Probabilistic generative model for learning object representations and scene rendering from partial observations.
result The model can infer 3D object representations and render scenes from arbitrary viewpoints.
This paper improves anomaly detection in lane rendering images for safer navigation.
problem Anomalies in lane rendering images can mislead drivers, posing safety risks.
method Proposes a four-phase pipeline using Transformer models, self-supervised pre-training, and fine-tuning.
result The pipeline enhances detection accuracy and reduces training time.
The paper uses differentiable rendering to generate semantic counterexamples for improving neural network robustness.
problem Neural networks' brittleness to semantic transformations.
method Differentiable rendering for generating realistic images that model semantic changes, combined with adversarial machine learning attacks.
result Semantic counterexamples improve generalization, robustness, and transferability of neural networks.
AR-GANs learn depth and DoF from unlabeled images using aperture rendering and focus cues.
problem Learning depth and DoF from unlabeled natural images with diverse viewpoints and shapes.
method Aperture rendering and focus cues to learn depth and DoF from unlabeled images.
result AR-GANs effectively learn depth and DoF from various datasets, including flower, bird, and face images.
A Human-in-the-Loop Bayesian Optimization framework for constraint-aware bioprocess development.
problem Bioprocess development
method Pareto Front Guided Sampling (PFGS) with Bayesian Optimization (BO)
result Systematic identification of high-performing, feasibility-compliant, and perturbation-resilient operating conditions.
Paper proposes a neural network for learning better importance sampling.
problem Improving variance reduction in Monte Carlo rendering.
method Uses a neural network to learn desired densities in the primary sample space of a rendering algorithm.
result Effective variance reduction demonstrated in practical scenarios.
NeRF-VAE generates 3D scenes with geometric structure from few images.
problem Generating 3D scenes from few images with geometric consistency.
method Combines NeRF and VAE, incorporating shared geometric structure.
result NeRF-VAE can infer and render geometrically-consistent scenes from unseen environments.
Automates UI implementation from designer images.
problem Automating UI implementation from designer images.
method Generative model training and imitation learning.
result 92.5% accuracy on Android Button attribute inference.
R package innsight interprets deep neural networks predictions.
problem Interpreting predictions of deep neural networks.
method Unified and user-friendly framework implementing feature attribution methods for neural networks, independent of deep learning library.
result Offers a variety of visualization tools for tabular, signal, image data or a combination.
Examines how algorithms affect user autonomy and information choice.
problem Impact of algorithmic recommendations on user autonomy and free choice.
method Double dichotomy analysis of user intentions and actions, prior and posterior information rearrangement.
result Algorithms can expand or limit user cognitive and social horizons.
Paper proposes meshAdv to generate adversarial 3D meshes for visual recognition.
problem Vulnerability of deep neural networks to adversarial examples.
method Differentiable renderer to manipulate shape and texture of 3D meshes.
result 3D meshes effectively attack classifiers and object detectors.
Improves spline quality and accuracy in computational microscopy.
problem Detecting slender, overlapping structures in microscopy images.
method Differentiable rendering approach for spline refinement.
result Achieves high reliability and sub-pixel accuracy.
Bayesian brain computes without noise, using correlated activity.
problem Trial-to-trial variability in brain activity is not noise but probabilistic encoding.
method Analytical study of correlated neural activity and synaptic plasticity.
result Deterministic spiking networks can perform Bayesian inference without noise.
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algor…
In this article, we propose a new algorithm for supervised learning methods, by which one can both capture the non-linearity in data and also find the best subset model. To produce an enhanced subset of the original variables, an ideal selection method should have the potential of adding a supplementary level of regres…
Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning. Deep Convolutional Networks (DCNs) have achieved great success in supervised tasks and as such have been widely employed in the semi-supervised learning. In this paper we…
Improves synthetic data for deep model training and adaptation.
problem Evaluating and improving synthetic data for deep learning models.
method Proposes a novel learned synthesis technique using generative models for shading and rendering, and uses an ensemble of models to generate datasets.
result Improves classifier performance on real data compared to state-of-the-art methods.
3D adversarial logos can fool object detectors in real-world settings.
problem Creating robust adversarial attacks in 3D rendering views.
method Constructing 3D adversarial logos via texture mapping and differentiable rendering.
result 3D adversarial logos are more versatile and robust than traditional adversarial patches.
A new metric for detecting out-of-distribution samples using neural rendering models.
problem Difficulty in detecting out-of-distribution samples with existing deep generative models.
method Derive metrics for out-of-distribution detection using a neural rendering model.
result Lower likelihood of latent variables is assigned to out-of-distribution samples.
DocParser parses document structures from renderings like PDFs and scans.
problem Parsing complete hierarchical document structures from renderings.
method End-to-end system with novel weak supervision approach.
result Significant improvement in document structure parsing performance.
Physics-informed learning framework for pH systems and EB-PBC control.
problem Control of port-Hamiltonian systems from trajectory data.
method Co-learning of pH system model and EB-PBC through alternating optimization.
result Proven stability and robustness of the learned controller.
Model predicts multi-agent trajectories using a differentiable simulator.
problem Predicting future positions of multiple interacting agents.
method Conditional recurrent variational neural networks (CVRNNs) with a kinematic bicycle model.
result Achieves state-of-the-art results on INTERACTION dataset.
The study characterizes the conditioning of the Gauss-Newton matrix in neural networks.
problem Understanding the conditioning of the Gauss-Newton matrix in neural networks.
method Theoretical analysis of the GN matrix in deep linear and ReLU networks, extending to residual connections and convolutional layers.
result Established tight bounds on the condition number of the GN matrix in neural networks.
Algorithm finds optimal affine transformation to minimize overall distortion.
problem Minimizing distortion in affine transformations.
method Riemannian geometry approach to define and minimize distortion.
result Mean distorting transformation found for minimizing overall distortion.
Learn object dynamics from unlabeled images.
problem Unsupervised learning of multiple object dynamics from unlabeled video sequences.
method Probabilistic model generating noisy positions, followed by non-linear rendering. Efficient inference method for querying the model.
result Efficient inference of object dynamics from unlabeled images.