{"ID":2899825,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.01204","arxiv_id":"2507.01204","title":"LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression","abstract":"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.","short_abstract":"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 im...","url_abs":"https://arxiv.org/abs/2507.01204","url_pdf":"https://arxiv.org/pdf/2507.01204v2","authors":"[\"Haotian Wu\",\"Gongpu Chen\",\"Pier Luigi Dragotti\",\"Deniz Gündüz\"]","published":"2025-07-01T21:48:16Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.IT\"]","methods":"[]","has_code":false}