# PatchINR: Patch-Based Implicit Neural Representations for Efficient and Scalable Inference

arXiv: https://arxiv.org/abs/2606.25534 · HTML: https://mlsanity.com/paper/2606.25534/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [MetaSDF: Meta-learning Signed Distance Functions](https://mlsanity.com/paper/2006.09662/) (2020)
- [Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs](https://mlsanity.com/paper/2111.15135/) (2021)
- [FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functions](https://mlsanity.com/paper/2312.02434/) (2023)
- [SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations](https://mlsanity.com/paper/2309.15848/) (2023)
- [DINER: Disorder-Invariant Implicit Neural Representation](https://mlsanity.com/paper/2211.07871/) (2022)
- [On Quantizing Implicit Neural Representations](https://mlsanity.com/paper/2209.01019/) (2022)
- [Nonparametric Teaching of Implicit Neural Representations](https://mlsanity.com/paper/2405.10531/) (2024)
- [CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture](https://mlsanity.com/paper/2201.12425/) (2022)
- [Learning Spatially Collaged Fourier Bases for Implicit Neural Representation](https://mlsanity.com/paper/2312.17018/) (2023)
- [Cicero: Addressing Algorithmic and Architectural Bottlenecks in Neural Rendering by Radiance Warping and Memory Optimizations](https://mlsanity.com/paper/2404.11852/) (2024)
- [ASMR: Activation-sharing Multi-resolution Coordinate Networks For Efficient Inference](https://mlsanity.com/paper/2405.12398/) (2024)
- [MINR: Efficient Implicit Neural Representations for Multi-Image Encoding](https://mlsanity.com/paper/2508.13471/) (2025)
- [Distribution-Aware Hadamard Quantization for Hardware-Efficient Implicit Neural Representations](https://mlsanity.com/paper/2508.13478/) (2025)
- [Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations](https://mlsanity.com/paper/2508.13481/) (2025)

## Abstract (arXiv)

Implicit Neural Representation (INR) provides an effective approach for continuous signal modeling, but classical per-pixel inference results in quadratic growth in inference count, leading to dramatically increased computational costs in high-resolution application scenarios. To address this issue, we propose a patch-based approach that treats non-overlapping patches as fundamental processing units and predicts entire pixel patches in a single forward pass, significantly reducing the number of inference queries required. To validate the effectiveness of our approach, we propose a hardware acceleration architecture on the Field Programmable Gate Array (FPGA) platform for the INR model, which features a configurable pipeline and supports dual-precision computation. Our patch-based INR achieves comparable reconstruction quality to pixel-level INR (34.97 dB PSNR with 2 x 2 patches) while reducing inference latency by 75% with only 0.6% parameter overhead.