The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: perceptual metrics, lpips, perceptual embeddings, representation learning, self-supervised learning, FR-IQA, image quality assessment, compression, data-free, ssim, bapps, 2afc, jnd
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We show how SOTA perceptual embeddings of the visual system can be constructed at inference-time with no training data or deep neural network features.
Abstract: We show how perceptual embeddings of the visual system can be constructed at inference-time with no training data or deep neural network features. Our perceptual embeddings are solutions to a weighted least squares (WLS) problem, defined at the pixel-level, and solved at inference-time, that can capture global and local image characteristics. The distance in embedding space is used to define a perceptual similary metric which we call \emph{LASI: Linear Autoregressive Similarity Index}. Experiments on full-reference image quality assessment datasets show LASI performs competitively with learned deep feature based methods like LPIPS \citep{zhang2018unreasonable} and PIM \citep{bhardwaj2020unsupervised}, at a similar computational cost to hand-crafted methods such as MS-SSIM \citep{wang2003multiscale}. We found that increasing the dimensionality of the embedding space consistently reduces the WLS loss while increasing performance on perceptual tasks, at the cost of increasing the computational complexity. LASI is fully differentiable, scales cubically with the number of embedding dimensions, and can be parallelized at the pixel-level. A Maximum Differentiation (MAD) competition \citep{wang2008maximum} between LASI and LPIPS shows that both methods are capable of finding failure points for the other, suggesting these metrics can be combined.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: representation learning for computer vision, audio, language, and other modalities
Submission Number: 2943
Loading