SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations

• URL: http://arxiv.org/abs/2309.15848v1
• Date: Wed, 27 Sep 2023 17:59:48 GMT
• Title: SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations
• Authors: Sharath Girish, Abhinav Shrivastava, Kamal Gupta
• Abstract summary: Implicit Neural Representations (INR) or neural fields have emerged as a popular framework to encode multimedia signals. We propose SHACIRA, a framework for compressing such feature grids with no additional post-hoc pruning/quantization stages. Our approach outperforms existing INR approaches without the need for any large datasets or domain-specifics.
• Score: 46.01969382873856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Implicit Neural Representations (INR) or neural fields have emerged as a popular framework to encode multimedia signals such as images and radiance fields while retaining high-quality. Recently, learnable feature grids proposed by Instant-NGP have allowed significant speed-up in the training as well as the sampling of INRs by replacing a large neural network with a multi-resolution look-up table of feature vectors and a much smaller neural network. However, these feature grids come at the expense of large memory consumption which can be a bottleneck for storage and streaming applications. In this work, we propose SHACIRA, a simple yet effective task-agnostic framework for compressing such feature grids with no additional post-hoc pruning/quantization stages. We reparameterize feature grids with quantized latent weights and apply entropy regularization in the latent space to achieve high levels of compression across various domains. Quantitative and qualitative results on diverse datasets consisting of images, videos, and radiance fields, show that our approach outperforms existing INR approaches without the need for any large datasets or domain-specific heuristics. Our project page is available at http://shacira.github.io .

Related papers

• Neural NeRF Compression [19.853882143024]
  Recent NeRFs utilize feature grids to improve rendering quality and speed. These representations introduce significant storage overhead. This paper presents a novel method for efficiently compressing a grid-based NeRF model.
  arXiv  Detail & Related papers  (2024-06-13T09:12:26Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• FPGA Resource-aware Structured Pruning for Real-Time Neural Networks [3.294652922898631]
  Pruning sparsifies a neural network, reducing the number of multiplications and memory. We propose a hardware-centric formulation of pruning, by formulating it as a knapsack problem with resource-aware tensor structures. Proposed method achieves reductions ranging between 55% and 92% in the DSP utilization and up to 81% in BRAM utilization.
  arXiv  Detail & Related papers  (2023-08-09T18:14:54Z)
• Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualization [16.961769402078264]
  Scene representation networks (SRNs) have been recently proposed for compression and visualization of scientific data. We address this shortcoming with an adaptively placed multi-grid SRN (APMGSRN) We also release an open-source neural volume rendering application that allows plug-and-play rendering with any PyTorch-based SRN.
  arXiv  Detail & Related papers  (2023-07-16T19:36:19Z)
• Modality-Agnostic Variational Compression of Implicit Neural Representations [96.35492043867104]
  We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR) Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression.
  arXiv  Detail & Related papers  (2023-01-23T15:22:42Z)
• Masked Wavelet Representation for Compact Neural Radiance Fields [5.279919461008267]
  Using a multi-layer perceptron to represent a 3D scene or object requires enormous computational resources and time. We present a method to reduce the size without compromising the advantages of having additional data structures. With our proposed mask and compression pipeline, we achieved state-of-the-art performance within a memory budget of 2 MB.
  arXiv  Detail & Related papers  (2022-12-18T11:43:32Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)
• Learning Enriched Features for Real Image Restoration and Enhancement [166.17296369600774]
  convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. We present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
  arXiv  Detail & Related papers  (2020-03-15T11:04:30Z)

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.