# LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression

arXiv: https://arxiv.org/abs/2507.01204 · HTML: https://mlsanity.com/paper/2507.01204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2025.

## Built on by (most cited first, 2 of 2)

- [Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models](https://mlsanity.com/paper/2509.05925/) (2025)
- [SemSteDiff: Generative Diffusion Model-based Coverless Semantic Steganography Communication](https://mlsanity.com/paper/2509.04803/) (2025)

## Abstract (arXiv)

We introduce and validate the lottery codec hypothesis, which states that untrained subnetworks within randomly initialized networks can serve as synthesis networks for overfitted image compression, achieving rate-distortion (RD) performance comparable to trained networks. This hypothesis leads to a new paradigm for image compression by encoding image statistics into the network substructure. Building on this hypothesis, we propose LotteryCodec, which overfits a binary mask to an individual image, leveraging an over-parameterized and randomly initialized network shared by the encoder and the decoder. To address over-parameterization challenges and streamline subnetwork search, we develop a rewind modulation mechanism that improves the RD performance. LotteryCodec outperforms VTM and sets a new state-of-the-art in single-image compression. LotteryCodec also enables adaptive decoding complexity through adjustable mask ratios, offering flexible compression solutions for diverse device constraints and application requirements.