相关论文: VoxNeuS: Enhancing Voxel-Based Neural Surface Reco…

This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. Existingmethods achieve varying degrees of success by using different surface representations. However, they all have their own…

We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural Kernel Fields (NKF) representation. It enjoys similar…

View selection is critical in active 3D neural reconstruction as it impacts the contents of training set and resulting final output quality. Recent view selection strategies emphasize the visibility when evaluating model uncertainty in…

We present a method for Sparse view reconstruction with surface element splatting that runs within 3 minutes on a consumer grade GPU. While few methods address sparse radiance field learning from noisy or unposed sparse cameras, shape…

Recent advances in neural reconstruction using posed image sequences have made remarkable progress. However, due to the lack of depth information, existing volumetric-based techniques simply duplicate 2D image features of the object surface…

Implicit Neural Representations (INRs) have emerged as a powerful paradigm for parameterizing physical fields, yet they often suffer from spectral bias and the computational expense of non-convex optimization. We introduce the Vekua Layer…

Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are available. Although recent efforts alleviate this issue by enhancing multi-view…

We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images, for novel view synthesis. Previous solutions, such as pixelNeRF, rely only on pixel-aligned features and suffer from feature…

Presenting a 3D scene from multiview images remains a core and long-standing challenge in computer vision and computer graphics. Two main requirements lie in rendering and reconstruction. Notably, SOTA rendering quality is usually achieved…

Recent advances in radiance field reconstruction, such as 3D Gaussian Splatting (3DGS), have achieved high-quality novel view synthesis and fast rendering by representing scenes with compositions of Gaussian primitives. However, 3D…

Surface-from-gradients (SfG) aims to recover a three-dimensional (3D) surface from its gradients. Traditional methods encounter significant challenges in achieving high accuracy and handling high-resolution inputs, particularly facing the…

Dynamic imaging is essential for analyzing various biological systems and behaviors but faces two main challenges: data incompleteness and computational burden. For many imaging systems, high frame rates and short acquisition times require…

Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to reconstruct high-quality surfaces from only sparse view…

Neural implicit surface representation techniques are in high demand for advancing technologies in augmented reality/virtual reality, digital twins, autonomous navigation, and many other fields. With their ability to model object surfaces…

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…

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…

Neural implicit functions have recently shown promising results on surface reconstructions from multiple views. However, current methods still suffer from excessive time complexity and poor robustness when reconstructing unbounded or…

Robust scene representation is essential for autonomous systems to safely operate in challenging low-visibility environments. Radar has a clear advantage over cameras and lidars in these conditions due to its resilience to environmental…

Implicit neural representations (INRs) have been successfully used to compress a variety of 3D surface representations such as Signed Distance Functions (SDFs), voxel grids, and also other forms of structured data such as images, videos,…

We present a novel way of approaching image-based 3D reconstruction based on radiance fields. The problem of volumetric reconstruction is formulated as a non-linear least-squares problem and solved explicitly without the use of neural…