Related papers: ElastoGen: 4D Generative Elastodynamics
Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures. The main reason is that most of the current generative models fail to explore…
Generating high-fidelity, physically interactive 3D simulated tabletop scenes is essential for embodied AI -- especially for robotic manipulation policy learning and data synthesis. However, current text- or image-driven 3D scene generation…
In this paper, we present InSeGAN, an unsupervised 3D generative adversarial network (GAN) for segmenting (nearly) identical instances of rigid objects in depth images. Using an analysis-by-synthesis approach, we design a novel GAN…
Deep generative models provide a systematic way to learn nonlinear data distributions, through a set of latent variables and a nonlinear "generator" function that maps latent points into the input space. The nonlinearity of the generator…
Manipulating elasto-plastic objects remains a significant challenge due to severe self-occlusion, difficulties of representation, and complicated dynamics. This work proposes a novel framework for elasto-plastic object manipulation with a…
Digital twin worlds with realistic interactive dynamics presents a new opportunity to develop generalist embodied agents in scannable environments with complex physical behaviors. To this end, we present GDGen (Generalized Representation…
Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle pose and appearance, enable downstream applications in…
The analysis of parametric and non-parametric uncertainties of very large dynamical systems requires the construction of a stochastic model of said system. Linear approaches relying on random matrix theory and principal componant analysis…
Diffusion models have revolutionized image generation in recent years, yet they are still limited to a few sizes and aspect ratios. We propose ElasticDiffusion, a novel training-free decoding method that enables pretrained text-to-image…
The emergence of 3D artificial intelligence-generated content (3D-AIGC) has enabled rapid synthesis of intricate geometries. However, a fundamental disconnect persists between AI-generated content and human-centric design paradigms, rooted…
The discovery of inorganic crystal structures with targeted properties is a significant challenge in materials science. Generative models, especially state-of-the-art diffusion models, offer the promise of modeling complex data…
4D generation has made remarkable progress in synthesizing dynamic 3D objects from input text, images, or videos. However, existing methods often represent motion as an implicit deformation field, which limits direct control and…
Most deep learning models are based on deep neural networks with multiple layers between input and output. The parameters defining these layers are initialized using random values and are "learned" from data, typically using stochastic…
In the era of deep learning, data is the critical determining factor in the performance of neural network models. Generating large datasets suffers from various difficulties such as scalability, cost efficiency and photorealism. To avoid…
Generative adversarial network (GAN) has been shown to be useful in various applications, such as image recognition, text processing and scientific computing, due its strong ability to learn complex data distributions. In this study, a…
World modeling has become a cornerstone in AI research, enabling agents to understand, represent, and predict the dynamic environments they inhabit. While prior work largely emphasizes generative methods for 2D image and video data, they…
In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and complex twisted…
Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance significantly degrades in dynamic environments. This…
Dynamic texture synthesis aims to generate sequences that are visually similar to a reference video texture and exhibit specific stationary properties in time. In this paper, we introduce a spatiotemporal generative adversarial network…
Deep learning techniques for improving fluid flow modelling have gained significant attention in recent years. Advanced deep learning techniques achieve great progress in rapidly predicting fluid flows without prior knowledge of the…