Related papers: Neu-PiG: Neural Preconditioned Grids for Fast Dyna…
Dynamic surface reconstruction of objects from point cloud sequences is a challenging field in computer graphics. Existing approaches either require multiple regularization terms or extensive training data which, however, lead to…
We introduce Neural Deformation Graphs for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects. Specifically, we implicitly model a deformation graph via a deep neural network. This neural deformation graph…
Recent methods for neural surface representation and rendering, for example NeuS, have demonstrated the remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8 hours), which…
We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on…
Neural surfaces learning has shown impressive performance in multi-view surface reconstruction. However, most existing methods use large multilayer perceptrons (MLPs) to train their models from scratch, resulting in hours of training for a…
Recent works have shown that Large Language Models (LLMs) can facilitate the grounding of instructions for robotic task planning. Despite this progress, most existing works have primarily focused on utilizing raw images to aid LLMs in…
Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging, yet reconstructing high-resolution 3D data remains computationally demanding. Non-Cartesian reconstructions require repeated non-uniform FFTs, and the commonly used…
Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. Unfortunately, this method fails for important cases such as highly…
We present GO-Surf, a direct feature grid optimization method for accurate and fast surface reconstruction from RGB-D sequences. We model the underlying scene with a learned hierarchical feature voxel grid that encapsulates multi-level…
We propose DynamicSurf, a model-free neural implicit surface reconstruction method for high-fidelity 3D modelling of non-rigid surfaces from monocular RGB-D video. To cope with the lack of multi-view cues in monocular sequences of deforming…
Neural implicit representations are widely used for 3D shape modeling due to their smoothness and compactness, but traditional MLP-based methods struggle with sharp features, such as edges and corners in CAD models, and require long…
Reconstructing high-quality 3D objects from sparse, partial observations from a single view is of crucial importance for various applications in computer vision, robotics, and graphics. While recent neural implicit modeling methods show…
We present a self-supervised method to learn dynamic 3D deformations of garments worn by parametric human bodies. State-of-the-art data-driven approaches to model 3D garment deformations are trained using supervised strategies that require…
Recent advances in neural implicit surfaces for multi-view 3D reconstruction primarily focus on improving large-scale surface reconstruction accuracy, but often produce over-smoothed geometries that lack fine surface details. To address…
Recently, Neural Radiance Fields (NeRF) is revolutionizing the task of novel view synthesis (NVS) for its superior performance. In this paper, we propose to synthesize dynamic scenes. Extending the methods for static scenes to dynamic…
We introduce a novel, data-driven approach for reconstructing temporally coherent 3D motion from unstructured and potentially partial observations of non-rigidly deforming shapes. Our goal is to achieve high-fidelity motion reconstructions…
Modeling the dynamics of deformable objects is challenging due to their diverse physical properties and the difficulty of estimating states from limited visual information. We address these challenges with a neural dynamics framework that…
We introduce FLAG-4D, a novel framework for generating novel views of dynamic scenes by reconstructing how 3D Gaussian primitives evolve through space and time. Existing methods typically rely on a single Multilayer Perceptron (MLP) to…
Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or…
Recent years have witnessed significant progress in the field of neural surface reconstruction. While the extensive focus was put on volumetric and implicit approaches, a number of works have shown that explicit graphics primitives such as…