Super-resolution (SR) and image generation are important tasks in computer vision and are widely adopted in real-world applications. Most existing methods, however, generate images only at fixed-scale magnification and suffer from over-smoothing and artifacts. Additionally, they do not offer enough diversity of output images nor image consistency at different scales. Most relevant work applied Implicit Neural Representation (INR) to the denoising diffusion model to obtain continuous-resolution yet diverse and high-quality SR results. Since this model operates in the image space, the larger the resolution of image is produced, the more memory and inference time is required, and it also does not maintain scale-specific consistency. We propose a novel pipeline that can super-resolve an input image or generate from a random noise a novel image at arbitrary scales. The method consists of a pre-trained auto-encoder, a latent diffusion model, and an implicit neural decoder, and their learning strategies. The proposed method adopts diffusion processes in a latent space, thus efficient, yet aligned with output image space decoded by MLPs at arbitrary scales. More specifically, our arbitrary-scale decoder is designed by the symmetric decoder w/o up-scaling from the pre-trained auto-encoder, and Local Implicit Image Function (LIIF) in series. The latent diffusion process is learnt by the denoising and the alignment losses jointly. Errors in output images are backpropagated via the fixed decoder, improving the quality of output images. In the extensive experiments using multiple public benchmarks on the two tasks i.e. image super-resolution and novel image generation at arbitrary scales, the proposed method outperforms relevant methods in metrics of image quality, diversity and scale consistency. It is significantly better than the relevant prior-art in the inference speed and memory usage.
We propose a simple architecture that combines the LDM and LIIF decoder for both arbitrary-scale SR and image generation. An auto-encoder consisting of an encoder and a symmetric decoder w/o upsampling is pre-trained. Our implicit neural decoder combines the convolutional decoder from the auto-encoder and MLP-based decoder, that can map to arbitrary-scale output images.
Upper Part: Overall process of proposed networks. Red line is a super-resolution process, and Blue line is a generation process. Lower Left Part: Detail architecture of Implicit Neural Decoder. It contains a series of auto-decoder Dφ and a neural decoding function fθ. Lower Right Part: Pipeline of two-stage alignment process.
@inproceedings{kim2024arbitraryscale,
title={Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder},
author={Kim, Jinseok and Kim, Tae-Kyun},
booktitle={CVPR},
year={2024}
}