CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture

Authors: Ruofan Liang, Hongyi Sun, Nandita Vijaykumar

ICLR 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we evaluate the performance and efficiency of Coord X for several signal fitting tasks, including images, videos and 3D shapes.
Researcher Affiliation Academia 1Department of Computer Science, University of Toronto 2Vector Institute, Canada
Pseudocode No No pseudocode or clearly labeled algorithm block is present.
Open Source Code No No explicit statement or link regarding open-source code for the methodology described in this paper.
Open Datasets Yes We randomly select 12 center-cropped images from DIV2K dataset (Agustsson & Timofte, 2017) to report the average PSNR.
Dataset Splits No No explicit training/test/validation dataset splits (e.g., percentages or sample counts) are provided.
Hardware Specification Yes All models are implemented on Py Torch (Paszke et al., 2019) and evaluated using an NVIDIA RTX3090 GPU.
Software Dependencies No The paper mentions 'Py Torch' and 'Adam optimizer' but does not specify their version numbers or versions for other software dependencies.
Experiment Setup Yes Unless otherwise specified, our experiments use 5-layer MLPs. The Coord X models have two FC layers after the fusion operation (Df = 2). Model hyperparameters such as learning rate, batch size, number of epochs, etc., are the same as those used in the corresponding baseline coord MLPs. ... We use the Adam optimizer (Kingma & Ba, 2014) during training.