Polynomial Implicit Neural Representations For Large Diverse Datasets

• URL: http://arxiv.org/abs/2303.11424v1
• Date: Mon, 20 Mar 2023 20:09:46 GMT
• Title: Polynomial Implicit Neural Representations For Large Diverse Datasets
• Authors: Rajhans Singh (1), Ankita Shukla (1), Pavan Turaga (1) ((1) Arizona State University)
• Abstract summary: Implicit neural representations (INR) have gained significant popularity for signal and image representation. Most INR architectures rely on sinusoidal positional encoding, which accounts for high-frequency information in data. Our approach addresses this gap by representing an image with a function and eliminates the need for positional encodings. The proposed Poly-INR model performs comparably to state-of-the-art generative models without any convolution, normalization, or self-attention.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Implicit neural representations (INR) have gained significant popularity for signal and image representation for many end-tasks, such as superresolution, 3D modeling, and more. Most INR architectures rely on sinusoidal positional encoding, which accounts for high-frequency information in data. However, the finite encoding size restricts the model's representational power. Higher representational power is needed to go from representing a single given image to representing large and diverse datasets. Our approach addresses this gap by representing an image with a polynomial function and eliminates the need for positional encodings. Therefore, to achieve a progressively higher degree of polynomial representation, we use element-wise multiplications between features and affine-transformed coordinate locations after every ReLU layer. The proposed method is evaluated qualitatively and quantitatively on large datasets like ImageNet. The proposed Poly-INR model performs comparably to state-of-the-art generative models without any convolution, normalization, or self-attention layers, and with far fewer trainable parameters. With much fewer training parameters and higher representative power, our approach paves the way for broader adoption of INR models for generative modeling tasks in complex domains. The code is available at \url{https://github.com/Rajhans0/Poly_INR}

Related papers

• Attention Beats Linear for Fast Implicit Neural Representation Generation [13.203243059083533]
  We propose Attention-based Localized INR (ANR) composed of a localized attention layer (LAL) and a global representation vector. With instance-specific representation and instance-agnostic ANR parameters, the target signals are well reconstructed as a continuous function.
  arXiv  Detail & Related papers  (2024-07-22T03:52:18Z)
• HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation [4.53411151619456]
  We propose a few-shot learning approach based on the hypernetwork paradigm that does not require gradient optimization during inference. We have developed an efficient method for generating a high-quality 3D object representation from a small number of images in a single step.
  arXiv  Detail & Related papers  (2024-02-02T16:10:29Z)
• Neural Fields with Thermal Activations for Arbitrary-Scale Super-Resolution [56.089473862929886]
  We present a novel way to design neural fields such that points can be queried with an adaptive Gaussian PSF. With its theoretically guaranteed anti-aliasing, our method sets a new state of the art for arbitrary-scale single image super-resolution.
  arXiv  Detail & Related papers  (2023-11-29T14:01:28Z)
• Beyond Learned Metadata-based Raw Image Reconstruction [86.1667769209103]
  Raw images have distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels. They are not widely adopted by general users due to their substantial storage requirements. We propose a novel framework that learns a compact representation in the latent space, serving as metadata.
  arXiv  Detail & Related papers  (2023-06-21T06:59:07Z)
• Progressive Fourier Neural Representation for Sequential Video Compilation [75.43041679717376]
  Motivated by continual learning, this work investigates how to accumulate and transfer neural implicit representations for multiple complex video data over sequential encoding sessions. We propose a novel method, Progressive Fourier Neural Representation (PFNR), that aims to find an adaptive and compact sub-module in Fourier space to encode videos in each training session. We validate our PFNR method on the UVG8/17 and DAVIS50 video sequence benchmarks and achieve impressive performance gains over strong continual learning baselines.
  arXiv  Detail & Related papers  (2023-06-20T06:02:19Z)
• T-former: An Efficient Transformer for Image Inpainting [50.43302925662507]
  A class of attention-based network architectures, called transformer, has shown significant performance on natural language processing fields. In this paper, we design a novel attention linearly related to the resolution according to Taylor expansion, and based on this attention, a network called $T$-former is designed for image inpainting. Experiments on several benchmark datasets demonstrate that our proposed method achieves state-of-the-art accuracy while maintaining a relatively low number of parameters and computational complexity.
  arXiv  Detail & Related papers  (2023-05-12T04:10:42Z)
• Neural Residual Flow Fields for Efficient Video Representations [5.904082461511478]
  Implicit neural representation (INR) has emerged as a powerful paradigm for representing signals, such as images, videos, 3D shapes, etc. We propose a novel INR approach to representing and compressing videos by explicitly removing data redundancy. We show that the proposed method outperforms the baseline methods by a significant margin.
  arXiv  Detail & Related papers  (2022-01-12T06:22:09Z)
• Meta-Learning Sparse Implicit Neural Representations [69.15490627853629]
  Implicit neural representations are a promising new avenue of representing general signals. Current approach is difficult to scale for a large number of signals or a data set. We show that meta-learned sparse neural representations achieve a much smaller loss than dense meta-learned models.
  arXiv  Detail & Related papers  (2021-10-27T18:02:53Z)
• Adversarial Generation of Continuous Images [31.92891885615843]
  In this paper, we propose two novel architectural techniques for building INR-based image decoders. We use them to build a state-of-the-art continuous image GAN. Our proposed INR-GAN architecture improves the performance of continuous image generators by several times.
  arXiv  Detail & Related papers  (2020-11-24T11:06:40Z)
• Locally Masked Convolution for Autoregressive Models [107.4635841204146]
  LMConv is a simple modification to the standard 2D convolution that allows arbitrary masks to be applied to the weights at each location in the image. We learn an ensemble of distribution estimators that share parameters but differ in generation order, achieving improved performance on whole-image density estimation.
  arXiv  Detail & Related papers  (2020-06-22T17:59:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.