Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos

S Jeon, I Cho, M Kim, WO Cho, SJ Kim - European Conference on …, 2024‏ - Springer
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 …

GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation

J Cai, Y Yang, W Yuan, Y He, Z Dong, L Bo… - arxiv preprint arxiv …, 2024‏ - arxiv.org
This paper studies the problem of estimating physical properties (system identification)
through visual observations. To facilitate geometry-aware guidance in physical property …

NeuSmoke: Efficient Smoke Reconstruction and View Synthesis with Neural Transportation Fields

J Qiu, R Cen, Z Li, H Yan, MM Cheng… - SIGGRAPH Asia 2024 …, 2024‏ - dl.acm.org
Novel view synthesis of smoke scenes presents a challenging problem. Previous neural
approaches have suffered from inadequate quality and inefficient training. We introduce …

PINR: A physics-integrated neural representation for dynamic fluid scenes

Z Zhao, S Zhou, X Lu, W Zeng, J Qian - Neurocomputing, 2025‏ - Elsevier
Recent research based on neural representation has achieved impressive results in
dynamic reconstruction. However, reconstructing high-fidelity dynamic fluid scenes from …

Generative Physical AI in Vision: A Survey

D Liu, J Zhang, AD Dinh, E Park, S Zhang… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by
enabling machines to create and interpret visual data with unprecedented sophistication …

OSN: infinite representations of dynamic 3D scenes from monocular videos

Z Song, J Li, B Yang - arxiv preprint arxiv:2407.05615, 2024‏ - arxiv.org
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 …

Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE

H Wu, H Wang, K Wang, W Wang, Y Tao… - Forty-first International …‏ - openreview.net
Fluid dynamics modeling has received extensive attention in the machine learning
community. Although numerous graph neural network (GNN) approaches have been …

ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Events

K Chen, Z Wang, L Wang - arxiv preprint arxiv:2409.14103, 2024‏ - arxiv.org
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 …

[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 …

[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 …