Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos
We propose a new framework for creating and easily manipulating 3D models of arbitrary
objects using casually captured videos. Our core ingredient is a novel hierarchy deformation …
objects using casually captured videos. Our core ingredient is a novel hierarchy deformation …
GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation
This paper studies the problem of estimating physical properties (system identification)
through visual observations. To facilitate geometry-aware guidance in physical property …
through visual observations. To facilitate geometry-aware guidance in physical property …
NeuSmoke: Efficient Smoke Reconstruction and View Synthesis with Neural Transportation Fields
Novel view synthesis of smoke scenes presents a challenging problem. Previous neural
approaches have suffered from inadequate quality and inefficient training. We introduce …
approaches have suffered from inadequate quality and inefficient training. We introduce …
PINR: A physics-integrated neural representation for dynamic fluid scenes
Recent research based on neural representation has achieved impressive results in
dynamic reconstruction. However, reconstructing high-fidelity dynamic fluid scenes from …
dynamic reconstruction. However, reconstructing high-fidelity dynamic fluid scenes from …
Generative Physical AI in Vision: A Survey
Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by
enabling machines to create and interpret visual data with unprecedented sophistication …
enabling machines to create and interpret visual data with unprecedented sophistication …
OSN: infinite representations of dynamic 3D scenes from monocular videos
It has long been challenging to recover the underlying dynamic 3D scene representations
from a monocular RGB video. Existing works formulate this problem into finding a single …
from a monocular RGB video. Existing works formulate this problem into finding a single …
Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE
Fluid dynamics modeling has received extensive attention in the machine learning
community. Although numerous graph neural network (GNN) approaches have been …
community. Although numerous graph neural network (GNN) approaches have been …
ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Events
Recent years have witnessed tremendous progress in the 3D reconstruction of dynamic
humans from a monocular video with the advent of neural rendering techniques. This task …
humans from a monocular video with the advent of neural rendering techniques. This task …
[PDF][PDF] Physics-Informed Neural Fields with Neural Implicit Surface for Fluid Reconstruction
Z Duan, Z Ren - 2024 - diglib.eg.org
Recovering fluid density and velocity from multi-view RGB videos poses a formidable
challenge. Existing solutions typically assume knowledge of obstacles and lighting, or are …
challenge. Existing solutions typically assume knowledge of obstacles and lighting, or are …
[PDF][PDF] Mass conservative neural networks
F Arend Torres - 2024 - edoc.unibas.ch
Neural networks have established themselves as a powerful tool for extracting insights from
vast amounts of data. However, with increasing use of deep learning in the natural sciences …
vast amounts of data. However, with increasing use of deep learning in the natural sciences …