Related papers: Estimating Neural Orientation Distribution Fields …
Neural implicit surface reconstruction using volume rendering techniques has recently achieved significant advancements in creating high-fidelity surfaces from multiple 2D images. However, current methods primarily target scenes with…
Several variants of Neural Radiance Fields (NeRFs) have significantly improved the accuracy of synthesized images and surface reconstruction of 3D scenes/objects. In all of these methods, a key characteristic is that none can train the…
Signed Distance Functions (SDFs) are vital implicit representations to represent high fidelity 3D surfaces. Current methods mainly leverage a neural network to learn an SDF from various supervisions including signed distances, 3D point…
Accurate 3D perception is essential for understanding the environment in autonomous driving. Recent advancements in 3D semantic occupancy prediction have leveraged camera-LiDAR fusion to improve robustness and accuracy. However, current…
Convolutional Neural Networks (CNNs) have shown to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical…
The human brain constitutes 2% of the total body mass, but consumes 20% of the oxygen. The rate of the brain's oxygen utilization can be determined from the knowledge of cerebral blood flow and oxygen extraction fraction (OEF). Therefore,…
Diffusion Magnetic Resonance Imaging (DMRI) is the only non-invasive imaging technique which is able to detect the principal directions of water diffusion as well as neurites density in the human brain. Exploiting the ability of Spherical…
Neural fields, also known as implicit neural representations (INRs), offer a powerful framework for modeling continuous geometry, but their effectiveness in high-dimensional scientific settings is limited by slow convergence and scaling…
Modelling of stellar radiative intensities in various spectral pass-bands plays an important role in stellar physics. At the same time the direct calculations of the high-resolution spectrum and then integrating it over the given spectral…
The recent achievements of Deep Learning rely on the test data being similar in distribution to the training data. In an ideal case, Deep Learning models would achieve Out-of-Distribution (OoD) Generalization, i.e. reliably make predictions…
Recent advances in Neural radiance fields (NeRF) have enabled high-fidelity scene reconstruction for novel view synthesis. However, NeRF requires hundreds of network evaluations per pixel to approximate a volume rendering integral, making…
Due to recent technological advances, large brain imaging data sets can now be collected. Such data are highly complex so extraction of meaningful information from them remains challenging. Thus, there is an urgent need for statistical…
Constructing a high-quality dense map in real-time is essential for robotics, AR/VR, and digital twins applications. As Neural Radiance Field (NeRF) greatly improves the mapping performance, in this paper, we propose a NeRF-based mapping…
As artificial intelligence and digital medicine increasingly permeate healthcare systems, robust governance frameworks are essential to ensure ethical, secure, and effective implementation. In this context, medical image retrieval becomes a…
Deep neural decision forest (NDF) achieved remarkable performance on various vision tasks via combining decision tree and deep representation learning. In this work, we first trace the decision-making process of this model and visualize…
Deep neural networks (DNNs) are widely applied for nowadays 3D surface reconstruction tasks and such methods can be further divided into two categories, which respectively warp templates explicitly by moving vertices or represent 3D…
Robust semantic segmentation of intraoperative image data could pave the way for automatic surgical scene understanding and autonomous robotic surgery. Geometric domain shifts, however, although common in real-world open surgeries due to…
Generalizable neural radiance field (NeRF) enables neural-based digital human rendering without per-scene retraining. When combined with human prior knowledge, high-quality human rendering can be achieved even with sparse input views.…
This paper proposes a deep-learning-based method for recovering a signed distance function (SDF) of a given hypersurface represented by an implicit level set function. Using the flexibility of constructing a neural network, we use an…
Reconstructing the high-fidelity surface from multi-view images, especially sparse images, is a critical and practical task that has attracted widespread attention in recent years. However, existing methods are impeded by the memory…