Related papers: Learning Signed Distance Functions from Noisy 3D P…

The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will…

Scene Completion is the task of completing missing geometry from a partial scan of a scene. Most previous methods compute an implicit representation from range data using a Truncated Signed Distance Function (T-SDF) computed on a 3D grid as…

Safety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learning-based object detection insufficiencies to ensure the intended functionality of Automated Driving Systems (ADS). This paper presents a…

Recently, building on the foundation of neural radiance field, various techniques have emerged to learn unsigned distance fields (UDF) to reconstruct 3D non-watertight models from multi-view images. Yet, a central challenge in UDF-based…

Existing deep learning methods for the reconstruction and denoising of point clouds rely on small datasets of 3D shapes. We circumvent the problem by leveraging deep learning methods trained on billions of images. We propose a method to…

Semantic analyses of object point clouds are largely driven by releasing of benchmarking datasets, including synthetic ones whose instances are sampled from object CAD models. However, learning from synthetic data may not generalize to…

A signed distance function (SDF) parametrized by an MLP is a common ingredient of neural surface reconstruction. We build on the successful recent method NeuS to extend it by three new components. The first component is to borrow the…

As the development of 3D sensors, registration of 3D data (e.g. point cloud) coming from different kind of sensor is dispensable and shows great demanding. However, point cloud registration between different sensors is challenging because…

Pre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains. However, due to the unordered and non-uniform density characteristics of point clouds, it is non-trivial…

We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance field (SDF). Our backbone builds upon recent transformer-based…

Point clouds are utilized in various 3D applications such as cross-reality (XR) and realistic 3D displays. In some applications, e.g., for live streaming using a 3D point cloud, real-time point cloud denoising methods are required to…

Point clouds are vital in computer vision tasks such as 3D reconstruction, autonomous driving, and robotics. However, TLS-acquired point clouds often contain virtual points from reflective surfaces, causing disruptions. This study presents…

Accurate and efficient environment representation is crucial for robotic applications such as motion planning, manipulation, and navigation. Signed distance functions (SDFs) have emerged as a powerful representation for encoding distance to…

The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many…

The reconstruction of high-quality shape geometry is crucial for developing freehand 3D ultrasound imaging. However, the shape reconstruction of multi-view ultrasound data remains challenging due to the elevation distortion caused by thick…

This paper proposes a method for estimating a surface that contains a given set of points from noisy measurements. More precisely, by assuming that the surface is described by the zero set of a function in the span of a given set of…

We propose a feed-forward method for dense Signed Distance Field (SDF) regression from unstructured image collections in less than three seconds, without camera calibration or post-hoc fusion. Our key insight is that the intermediate…

We propose 3DSmoothNet, a full workflow to match 3D point clouds with a siamese deep learning architecture and fully convolutional layers using a voxelized smoothed density value (SDV) representation. The latter is computed per interest…

\textit{Implicit neural representations} (INRs) have emerged as a promising framework for representing signals in low-dimensional spaces. This survey reviews the existing literature on the specialized INR problem of approximating…

Neural Signed Distance Functions (SDFs) excel at reconstructing watertight manifolds but fail on thin structures and open boundaries due to strict inside--outside constraints. Conversely, Unsigned Distance Fields (UDFs) accommodate general…