相关论文: Estimation of rheological parameters for unstained…

As an extension of isotropic Gaussian random fields and Q-Wiener processes on d-dimensional spheres, isotropic Q-fractional Brownian motion is introduced and sample H\"older regularity in space-time is shown depending on the regularity of…

Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \cite{ost2021neural} extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy…

We propose a novel meshless method to achieve super resolution from scattered data obtained from sparse, randomly positioned sensors such as the particle tracers of particle tracking velocimetry. The method combines K Nearest Neighbor…

Extending deterministic compartments pharmacokinetic models as diffusions seems not realistic on biological side because paths of these stochastic processes are not smooth enough. In order to extend one compartment intra-veinous bolus…

Sampling from unnormalized densities presents a fundamental challenge with wide-ranging applications, from posterior inference to molecular dynamics simulations. Continuous flow-based neural samplers offer a promising approach, learning a…

Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational costs or poor quality of the generated saliency maps. To…

The transport of bio-particles in viscous flows exhibits a rich variety of dynamical behaviour, such as morphological transitions, complex orientation dynamics or deformations. Characterising such complex behaviour under well controlled…

The peculiar velocity field of the local Universe provides direct insights into its matter distribution and the underlying theory of gravity, and is essential in cosmological analyses for modelling deviations from the Hubble flow. Numerous…

We numerically investigate the feasibility and limits of jointly estimating flow fields and unknown particle properties (e.g., position, size, and density) from Lagrangian particle tracking (LPT) data. LPT offers time-resolved, volumetric…

Complex fluids such as emulsions, colloidal gels, polymer or surfactant solutions are all characterized by the existence of a "microstructure" which may couple to an external flow on timescales that are easily probed in experiments. Such a…

In recent years, Neural Radiance Fields (NeRF) have emerged as a powerful tool for 3D reconstruction and novel view synthesis. However, the computational cost of NeRF rendering and degradation in quality due to the presence of artifacts…

Motion free reconstruction of compressively sampled cardiac perfusion MR images is a challenging problem. It is due to the aliasing artifacts and the rapid contrast changes in the reconstructed perfusion images. In addition to the…

Extracting physical dynamical system parameters from recorded observations is key in natural science. Current methods for automatic parameter estimation from video train supervised deep networks on large datasets. Such datasets require…

We present MovingParts, a NeRF-based method for dynamic scene reconstruction and part discovery. We consider motion as an important cue for identifying parts, that all particles on the same part share the common motion pattern. From the…

Semantic Segmentation is an important module for autonomous robots such as self-driving cars. The advantage of video segmentation approaches compared to single image segmentation is that temporal image information is considered, and their…

Accurate velocity estimation is critical in mobile robotics, particularly for driver assistance systems and autonomous driving. Wheel odometry fused with Inertial Measurement Unit (IMU) data is a widely used method for velocity estimation;…

Recovering the 3D structure of the scene from images yields useful information for tasks such as shape and scene recognition, object detection, or motion planning and object grasping in robotics. In this thesis, we introduce a general…

We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. This task, which is often applied to novel view synthesis, is recently revolutionized…

Adopting Neural Radiance Fields (NeRF) to long-duration dynamic sequences has been challenging. Existing methods struggle to balance between quality and storage size and encounter difficulties with complex scene changes such as topological…

We propose a novel differentiable vortex particle (DVP) method to infer and predict fluid dynamics from a single video. Lying at its core is a particle-based latent space to encapsulate the hidden, Lagrangian vortical evolution underpinning…