DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization DNGaussian:使用全局-局部深度归一化优化稀疏视图3D高斯辐射场 论文链接: https://arxiv.org/abs/2403.06912 论文作者 Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu 内容简介...
3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduces a new co-regularization perspective for improving sparse-view 3DGS. When ...
3DGS + 稀疏重建 LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting https://arxiv.org/abs/2408.00254 Zhenyu Bao, Guibiao Liao, Kaichen Zhou, Kanglin Liu, Qing Li, Guoping Qiu 北京大学、鹏程实验室、University of Nottingham 尽管原始 3D 高斯分层 (3DGS) 实现了照片级逼真的新型视...
文章链接:[2408.00254] LoopSparseGS: Loop Based Sparse-View ... 项目主页:GitHub - pcl3dv/LoopSparseGS: The official reposit... 尽管原始的三维高斯泼溅( 3DGS )实现了真实感的新颖视图合成( NVS )性能,但在输入视图稀疏的情况下,其渲染质量显著下降。这种性能下降主要是由稀疏输入产生的初始点数量有限、...
Novel view synthesis via Neural Radiance Fields (NeRFs) or 3D Gaussian Splatting (3DGS) typically necessitates dense observations with hundreds of input images to circumvent artifacts. We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images, ...
This is the official repository for our CVPR 2024 paperDNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization. Paper|Project|Video Installation Tested on Ubuntu 18.04, CUDA 11.3, PyTorch 1.12.1
《InstantSplat：Unbounded Sparseview Posefree Gaussian Splatting in 40 Seconds》论文分享的核心要点如下：方法概述：InstantSplat是一种高效的新视图合成方法，旨在处理大规模场景、稀疏视图和无姿态条件。能够在不到一分钟内从稀疏和无姿态的图像中重建出高质量的3D场景，并生成准确的新视图。主要贡献：为...
This paper introduces DNGaussian, a depth-regularized framework based on 3D Gaussian radiance fields, offering real-time and high-quality few-shot novel view synthesis at low costs. Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splat...
3.4. Training Sparse View 3D Language Fields 在以往针对密集输入的3D语言领域表示方法中,训练语义特征时会放弃RGB监督。然而,在稀疏输入设置下,如果仅仅依赖语义损失来训练高斯模型,它们往往会变得过分拉长或过大,无法准确捕捉场景的正确几何分布。这完全是因为语义图提供的信息非常有限且区域化,几乎每个区域内部没有额...
3D semantic field learning is crucial for applications like autonomous navigation, AR/VR, and robotics, where accurate comprehension of 3D scenes from limited viewpoints is essential. Existing methods struggle under sparse view conditions, relying on inefficient per-scene multi-view optimizations, which ...