spherical harmonic
PulseAugur coverage of spherical harmonic — every cluster mentioning spherical harmonic across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New SH-WRNN model uses spherical harmonics for neural network weights
Researchers have introduced a novel neural network architecture called SH-WRNN, which replaces static weight matrices with a continuous field defined by spherical harmonics. This approach allows the network to dynamical…
-
Tutorial Explores Rotational Equivariance in Machine Learning
This tutorial offers a comprehensive introduction to rotational equivariance in machine learning, particularly for 3D data. It explains how predictions should remain consistent regardless of the input's coordinate frame…
-
PhysWave uses physics priors for controllable spatial audio generation
Researchers have developed PhysWave, a novel physics-guided latent diffusion model designed for controllable spatial audio generation. This model unifies natural language and trajectory control through a shared waypoint…
-
New PAGS framework improves photoacoustic tomography with speed-of-sound adaptation
Researchers have developed PAGS, a novel framework for photoacoustic computed tomography (PACT) that addresses the challenge of unknown speed-of-sound heterogeneity. This method uses speed-of-sound-adaptive Gaussian spl…
-
AI models for physics: Caltech professor pioneers structure-driven approach
Anima Anandkumar, a professor at the California Institute of Technology, has pioneered the development of AI models for complex physical systems, challenging the prevailing notion that scale is the only path to progress…
-
New frameworks tackle scale mismatch and rotation in point-cloud registration
Two new research papers introduce novel frameworks for point-cloud registration, a critical task in 3D perception for robotics. The first, R-SLPR, addresses the challenge of aligning small or incomplete point clouds wit…
-
Meshless Domain Randomization Enhances 3D Gaussian Splatting for Sim-to-Real Transfer
Researchers have developed a novel meshless domain randomization technique for 3D Gaussian Splatting (3DGS) to improve the transfer of models from simulation to the real world. This method perturbs the parameter space o…
-
KidSat model enhanced for poverty prediction using satellite imagery
Researchers have enhanced the KidSat framework to improve the accuracy of poverty prediction using satellite imagery. The updated pipeline incorporates refined data preprocessing, a systematic image quality assessment t…
-
New BubbleSH Dataset Enables Data-Driven Modeling of Bubbly Flows
Researchers have introduced BubbleSH, a new dataset designed for data-driven modeling of bubbly flows. This dataset captures transient, three-dimensional bubble-swarm dynamics from high-fidelity simulations, providing d…
-
New Gabor function improves 3D scene appearance modeling
Researchers have developed a new method for representing complex appearance effects in 3D scene reconstruction, moving beyond traditional Spherical Harmonics (SH). Their work introduces the Normalized Anisotropic Spheri…
-
Spherical Voronoi framework enhances 3D Gaussian Splatting appearance modeling
Researchers have introduced Spherical Voronoi (SV) as a novel framework for representing appearance in 3D radiance field methods like 3D Gaussian Splatting. This approach partitions the directional domain into learnable…