Lune

ICML2025Top-tier venue

Exploring Invariance in Images through One-way Wave Equations

Yinpeng Chen, Dongdong Chen, Xiyang Dai, Mengchen Liu, Yinan Feng, Youzuo Lin, Lu Yuan, Zicheng Liu

Abstract

In this paper, we empirically demonstrate that natural images can be reconstructed with high fidelity from compressed representations using a simple first-order norm-plus-linear autoregressive (FINOLA) process-without relying on explicit positional information. Through systematic analysis, we observe that the learned coefficient matrices (A and B) in FINOLA are typically invertible, and their product, AB -1 , is diagonalizable across training runs. This structure enables a striking interpretation: FINOLA's latent dynamics resemble a system of one-way wave equations evolving in a compressed latent space. Under this framework, each image corresponds to a unique solution of these equations. This offers a new perspective on image invariance, suggesting that the underlying structure of images may be governed by simple, invariant dynamic laws. Our findings shed light on a novel avenue for understanding and modeling visual data through the lens of latent-space dynamics and wave propagation.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale cites A Simple Framework for Contrastive Learning of Visual Representations
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale cites Language Models are Few-Shot Learners
  • Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning cites A Simple Framework for Contrastive Learning of Visual Representations
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on28

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  3. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  4. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  5. Bootstrap Your Own Latent - A New Approach to Self-Supervised LearningJean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec et al.NeurIPS 2020 · 9,171 citations

Related papers

  1. Learning Physics Constrained Dynamics Using AutoencodersTsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, Peter J. RamadgeNeurIPS 2022 · 39 citations
  2. High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable modelValentin Schmutz, Ali Haydaroglu, Shuqi Wang, Yixiao Feng et al.NeurIPS 2025 · 9 citations
  3. Idempotent Learned Image Compression with Right-InverseYanghao Li, Tongda Xu, Yan Wang, Jingjing Liu et al.NeurIPS 2023 · 8 citations
  4. Fitted Neural Lossless Image CompressionZhe Zhang, Zhenzhong Chen, Shan LiuCVPR 2025
  5. FARMER: Flow AutoRegressive Transformer over PixelsGuangting Zheng, Qinyu Zhao, Tao Yang, Fei Xiao et al.CVPR 2026 · 17 citations
Dusk over the sea between two cliffs drawn in fine vertical lines