Related papers: VoxNeuS: Enhancing Voxel-Based Neural Surface Reco…

Recent advances in neural rendering have enabled highly photorealistic 3D scene reconstruction and novel view synthesis. Despite this progress, current state-of-the-art methods struggle to reconstruct high frequency detail, due to factors…

Neural rendering has demonstrated remarkable success in dynamic scene reconstruction. Thanks to the expressiveness of neural representations, prior works can accurately capture the motion and achieve high-fidelity reconstruction of the…

Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem of surface…

Neural radiance fields have made a remarkable breakthrough in the novel view synthesis task at the 3D static scene. However, for the 4D circumstance (e.g., dynamic scene), the performance of the existing method is still limited by the…

We introduce an image upscaling technique tailored for 3D Gaussian Splatting (3DGS) on lightweight GPUs. Compared to 3DGS, it achieves significantly higher rendering speeds and reduces artifacts commonly observed in 3DGS reconstructions.…

Implicit Neural Representations (INRs) that learn Signed Distance Functions (SDFs) from point cloud data represent the state-of-the-art for geometrically accurate 3D scene reconstruction. However, training these Neural SDFs often requires…

Deep-neural-network-based image reconstruction has demonstrated promising performance in medical imaging for under-sampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is…

Accurate spatiotemporal image reconstruction methods are needed for a wide range of biomedical research areas but face challenges due to data incompleteness and computational burden. Data incompleteness arises from the undersampling often…

The task of reconstructing detailed 3D human body models from images is interesting but challenging in computer vision due to the high freedom of human bodies. In order to tackle the problem, we propose a coarse-to-fine method to…

We present NeRFVS, a novel neural radiance fields (NeRF) based method to enable free navigation in a room. NeRF achieves impressive performance in rendering images for novel views similar to the input views while suffering for novel views…

In this paper we describe a parallel implicit method based on radial basis functions (RBF) for surface reconstruction. The applicability of RBF methods is hindered by its computational demand, that requires the solution of linear systems of…

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images,…

This paper proposes GradientSurf, a novel algorithm for real time surface reconstruction from monocular RGB video. Inspired by Poisson Surface Reconstruction, the proposed method builds on the tight coupling between surface, volume, and…

We proposed a generalized method, NeuralSSD, for reconstructing a 3D implicit surface from the widely-available point cloud data. NeuralSSD is a solver-based on the neural Galerkin method, aimed at reconstructing higher-quality and accurate…

We propose a novel deep reinforcement learning-based approach for 3D object reconstruction from monocular images. Prior works that use mesh representations are template based. Thus, they are limited to the reconstruction of objects that…

Neural rendering methods have gained significant attention for their ability to reconstruct 3D scenes from 2D images. The core idea is to take multiple views as input and optimize the reconstructed scene by minimizing the uncertainty in…

Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing…

Neural implicit 3D representations have emerged as a powerful paradigm for reconstructing surfaces from multi-view images and synthesizing novel views. Unfortunately, existing methods such as DVR or IDR require accurate per-pixel object…

Achieving high-fidelity 3D surface reconstruction while preserving fine details remains challenging, especially in the presence of materials with complex reflectance properties and without a dense-view setup. In this paper, we introduce a…

While originally developed for novel view synthesis, Neural Radiance Fields (NeRFs) have recently emerged as an alternative to multi-view stereo (MVS). Triggered by a manifold of research activities, promising results have been gained…