Implicit Neural Representation (INR) has gained increasing popularity as a data representation method, serving as a prerequisite for innovative generation models. Unlike gradient-based methods, which exhibit lower efficiency in inference, the adoption of hyper-network for generating parameters in Multi-Layer Perceptrons (MLP), responsible for executing INR functions, has surfaced as a promising and efficient alternative. However, as a global continuous function, MLP is challenging in modeling highly discontinuous signals, resulting in slow convergence during the training phase and inaccurate reconstruction performance. Moreover, MLP requires massive representation parameters, which implies inefficiencies in data representation. In this paper, we propose a novel Attention-based Localized INR (ANR) composed of a localized attention layer (LAL) and a global MLP that integrates coordinate features with data features and converts them to meaningful outputs. Subsequently, we design an instance representation framework that delivers a transformer-like hyper-network to represent data instances as a compact representation vector. With instance-specific representation vector and instance-agnostic ANR parameters, the target signals are well reconstructed as a continuous function. We further address aliasing artifacts with variational coordinates when obtaining the super-resolution inference results. Extensive experimentation across four datasets showcases the notable efficacy of our ANR method, e.g. enhancing the PSNR value from 37.95dB to 47.25dB on the CelebA dataset. Code is released at https://github.com/Roninton/ANR.
Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机与软件学院);Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ)(广东省人工智能与数字经济实验室(深圳));Peng Cheng Laboratory(鹏城实验室)
Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations
School of Computation, Information and Technology, Technical University of Munich(慕尼黑工业大学计算、信息与技术学院);Helmholtz AI, Helmholtz Munich - German Research Center for Environmental Health(亥姆霍兹慕尼黑德国环境健康研究中心亥姆霍兹人工智能研究所);School of Biomedical Engineering and Imaging Sciences, King’s College London(伦敦国王学院生物医学工程与影像科学学院)
3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models
National University of Singapore(新加坡国立大学);Technical University of Munich(慕尼黑工业大学);Bernard M. Baruch College(伯纳德·M·巴鲁克学院);Stanford University(斯坦福大学);Computational Design Institute(计算设计研究所);Adobe(奥多比公司)
Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features
Institute of Computational Imaging, Beijing Information Science and Technology University(北京信息科技大学计算成像研究所);College of Computer Science (College of Software), Inner Mongolia University(内蒙古大学计算机学院(软件学院))
TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization
School of Artificial Intelligence, Jilin University(吉林大学人工智能学院);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院)
Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Series
ShanghaiTech University(上海科技大学);Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海智能视觉与成像工程研究中心);Shanghai Engineering Research Center of Energy Efficient and Custom AI IC(上海高效节能定制人工智能芯片工程研究中心)
本文提出 Taylor3DNet,利用离散地标点及其 Taylor 级数系数表示三维隐式场,将查询点评估简化为低阶 Taylor 计算,从而在多种重建任务中显著加速且不降低精度。
SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
Shandong University China;City University of Hong Kong China;Hong Kong University of Science;The University of Hong Kong China;Texas A\&M University USA;Shandong University;City University of Hong Kong;The University of Hong Kong;Texas A\&M University