MINER: Multiscale Implicit Neural Representations
We introduce a new neural signal model designed for efficient high-resolution representation of large-scale signals. The key innovation in our multiscale implicit neural representation (MINER) is an internal representation via a Laplacian pyramid, which provides a sparse multiscale decomposition of the signal that captures orthogonal parts of the signal across scales. We leverage the advantages of the Laplacian pyramid by representing small disjoint patches of the pyramid at each scale with a small MLP. This enables the capacity of the network to adaptively increase from coarse to fine scales, and only represent parts of the signal with strong signal energy. The parameters of each MLP are optimized from coarse-to-fine scale which results in faster approximations at coarser scales, thereby ultimately an extremely fast training process. We apply MINER to a range of large-scale signal representation tasks, including gigapixel images and very large point clouds, and demonstrate that it requires fewer than 25% of the parameters, 33% of the memory footprint, and 10% of the computation time of competing techniques such as ACORN to reach the same representation accuracy.
Code (1)
Tasks
Image ReconstructionSimilar Papers 제목 키워드 기반
Rethinking Implicit Spatial Representation in Visuomotor Policy Learning
Generative model-based imitation learning has become a widely adopted paradigm for robotic manipulation, where policy performance depends critically on the conditioned visual representations. Although spatial softmax-bas…
MGNNI: Multiscale Graph Neural Networks with Implicit Layers
Recently, implicit graph neural networks (GNNs) have been proposed to capture long-range dependencies in underlying graphs. In this paper, we introduce and justify two weaknesses of implicit GNNs: the constrained express…
Graph ClassificationGraph Neural NetworkNode ClassificationScaling Implicit Fields via Hypernetwork-Driven Multiscale Coordinate Transformations
Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing signals such as images, 3D shapes, signed distance fields, and radiance fields. While significant progress has been made in arch…
Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting
Mesoscale ocean dynamics play a critical role in climate systems, governing heat transport, hurricane genesis, and drought patterns. However, simulating these processes at high resolution remains computationally prohibit…
Computational EfficiencyMultiscale porosity in mesoporous bioglass 3D-printed scaffolds for bone regeneration
In order to increase the bone forming ability of MBG-PCL composite scaffold, microporosity was created in the struts of 3D-printed MBG-PCL scaffolds for the manufacturing of a construct with a multiscale porosity consist…