Related papers: FDIF: Formula-Driven supervised Learning with Impl…

Differentiable physics is a powerful tool in computer vision and robotics for scene understanding and reasoning about interactions. Existing approaches have frequently been limited to objects with simple shape or shapes that are known in…

We present Gradient-SDF, a novel representation for 3D geometry that combines the advantages of implict and explicit representations. By storing at every voxel both the signed distance field as well as its gradient vector field, we enhance…

Synthetic datasets are being recognized in the deep learning realm as a valuable alternative to exhaustively labeled real data. One such synthetic data generation method is Formula Driven Supervised Learning (FDSL), which can provide an…

We present a Deep Differentiable Simplex Layer (DDSL) for neural networks for geometric deep learning. The DDSL is a differentiable layer compatible with deep neural networks for bridging simplex mesh-based geometry representations (point…

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in…

We investigate the generalization capabilities of neural signed distance functions (SDFs) for learning 3D object representations for unseen and unlabeled point clouds. Existing methods can fit SDFs to a handful of object classes and boast…

Probabilistic diffusion models have achieved state-of-the-art results for image synthesis, inpainting, and text-to-image tasks. However, they are still in the early stages of generating complex 3D shapes. This work proposes Diffusion-SDF, a…

Medical image segmentation plays an important role in accurately identifying and isolating regions of interest within medical images. Generative approaches are particularly effective in modeling the statistical properties of segmentation…

Differentiable rendering is an essential operation in modern vision, allowing inverse graphics approaches to 3D understanding to be utilized in modern machine learning frameworks. Explicit shape representations (voxels, point clouds, or…

Machine learning-based approaches outperform competing methods in most disciplines relevant to diagnostic radiology. Interventional radiology, however, has not yet benefited substantially from the advent of deep learning, in particular…

Neural signed distance functions (SDFs) are emerging as an effective representation for 3D shapes. State-of-the-art methods typically encode the SDF with a large, fixed-size neural network to approximate complex shapes with implicit…

High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields. The spatial information in these images reflects the object's texture features, while the spectral information…

Methods allowing the synthesis of realistic cell shapes could help generate training data sets to improve cell tracking and segmentation in biomedical images. Deep generative models for cell shape synthesis require a light-weight and…

Medical image segmentation has been significantly advanced with the rapid development of deep learning (DL) techniques. Existing DL-based segmentation models are typically discriminative; i.e., they aim to learn a mapping from the input…

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…

Medical image segmentation is challenging due to the diversity of medical images and the lack of labeled data, which motivates recent developments in federated semi-supervised learning (FSSL) to leverage a large amount of unlabeled data…

Segmentation of medical images constitutes an essential component of medical image analysis, providing the foundation for precise diagnosis and efficient therapeutic interventions in clinical practices. Despite substantial progress, most…

Deep Implicit Functions (DIFs) represent 3D geometry with continuous signed distance functions learned through deep neural nets. Recently DIFs-based methods have been proposed to handle shape reconstruction and dense point correspondences…

Recent advances in 3D deep learning have shown that it is possible to train highly effective deep models for 3D shape generation, directly from 2D images. This is particularly interesting since the availability of 3D models is still limited…

Pretraining with large-scale 3D volumes has a potential for improving the segmentation performance on a target medical image dataset where the training images and annotations are limited. Due to the high cost of acquiring pixel-level…