PatchINR: Patch-Based Implicit Neural Representations for Efficient and Scalable Inference
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Ray-Patch: An Efficient Querying for Light Field Transformers
In this paper we propose the Ray-Patch querying, a novel model to efficiently query transformers to decode implicit representations into target views. Our Ray-Patch decoding reduces the computational footprint and increa…
Shape As Points: A Differentiable Poisson Solver
In recent years, neural implicit representations gained popularity in 3D reconstruction due to their expressiveness and flexibility. However, the implicit nature of neural implicit representations results in slow inferen…
3D ReconstructionGPUSurface ReconstructionSpatial Autoregressive Modeling of DINOv3 Embeddings for Unsupervised Anomaly Detection
DINO models provide rich patch-level representations that have recently enabled strong performance in unsupervised anomaly detection (UAD). Most existing methods extract patch embeddings from ``normal'' images and model …
Unsupervised Anomaly DetectionLRMIL: Efficient Low-Resolution Multiple Instance Learning via High-Resolution Knowledge Distillation for Whole Slide Image Classification
Multiple instance learning (MIL) has become a standard paradigm for whole slide image (WSI) analysis in digital pathology, as it enables slide-level prediction without dense annotations. Existing MIL methods typically re…
Multiple Instance LearningKnowledge DistillationImage ClassificationPatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
Implicit surface representations, such as signed-distance functions, combined with deep learning have led to impressive models which can represent detailed shapes of objects with arbitrary topology. Since a continuous fu…
Point Cloud Completion