Neurbf: A neural fields representation with adaptive radial basis functions
We present a novel type of neural fields that uses general radial bases for signal
representation. State-of-the-art neural fields typically rely on grid-based representations for …
representation. State-of-the-art neural fields typically rely on grid-based representations for …
Gaussianobject: High-quality 3d object reconstruction from four views with gaussian splatting
Reconstructing and rendering 3D objects from highly sparse views is of critical importance
for promoting applications of 3D vision techniques and improving user experience …
for promoting applications of 3D vision techniques and improving user experience …
Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light Field
In this paper, we address the problem of simultaneous relighting and novel view synthesis of
a complex scene from multi-view images with a limited number of light sources. We propose …
a complex scene from multi-view images with a limited number of light sources. We propose …
Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs
The multi-plane representation has been highlighted for its fast training and inference across
static and dynamic neural radiance fields. This approach constructs relevant features via …
static and dynamic neural radiance fields. This approach constructs relevant features via …
HourglassNeRF: Casting an Hourglass as a Bundle of Rays for Few-shot Neural Rendering
Recent advancements in the Neural Radiance Field (NeRF) have bolstered its capabilities
for novel view synthesis, yet its reliance on dense multi-view training images poses a …
for novel view synthesis, yet its reliance on dense multi-view training images poses a …
TVNeRF: Improving few-view neural volume rendering with total variation maximization
Y Zhang, J Wei, B Zhou, F Li, Y **e, J Liu - Knowledge-Based Systems, 2024 - Elsevier
Abstract Neural Radiance Fields (NeRF) has profoundly impacted few-shot novel view
synthesis and 3D reconstruction with its innovative rendering techniques and high-quality …
synthesis and 3D reconstruction with its innovative rendering techniques and high-quality …
基于神经辐射场的新视角合成研究进展
何高湘， 朱斌， 解博， 陈熠 - Laser & Optoelectronics Progress, 2024 - opticsjournal.net
摘要作为神经渲染领域中备受关注的研究方向之一, 神经辐射场(NeRF) 提供了一种新颖的隐式
三维场景表示方式. 该方法将场景构想为由无数发光粒子组成的介质, 并应用可微分的体积渲染 …
三维场景表示方式. 该方法将场景构想为由无数发光粒子组成的介质, 并应用可微分的体积渲染 …
[PDF][PDF] Scene-Level Reconstruction with Sparse Inputs
C Yang - 2024 - chensjtu.github.io
3D scene reconstruction from images has emerged as a fundamental technology that
underpins numerous real-world applications. In autonomous driving, accurate 3D scene …
underpins numerous real-world applications. In autonomous driving, accurate 3D scene …
Refined Tensorial Radiance Field: Harnessing coordinate based networks for novel view synthesis from sparse inputs
The multi-plane encoding approach has been highlighted for its ability to serve as static and
dynamic neural radiance fields without sacrificing generality. This approach constructs …
dynamic neural radiance fields without sacrificing generality. This approach constructs …
[HTML][HTML] 基于傅里叶频域截断的神经辐射场优化
殷泽众， 郭茂祖， 田乐 - 智能系统学报, 2024 - html.rhhz.net
神经辐射场(neural radiance fields, NeRF) 作为一种通用的场景表达方法, 可以更好地理解三维
世界的同时创造出更加逼真的感官体验. 然而在实际应用中, 输入图像较少导致重建效果不佳是 …
世界的同时创造出更加逼真的感官体验. 然而在实际应用中, 输入图像较少导致重建效果不佳是 …