PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokens

arXiv:2503.09368v2 Announce Type: replace Abstract: Despite recent progress in learned image compression, current image codecs still struggle to maintain realistic reconstructions at low bit-rates, often producing structured artifacts such as grid patterns or repetitive textures, even when trained with perceptual or adversarial losses. We introduce PerCoV2, an ultra-low bit-rate perceptual image compression system that unifies semantic tokenization, flow-based generation, and learned entropy modeling within a single framework. Building on the fully open flow-based SANA architecture, PerCoV2 introduces a novel resolution-adaptive 1D query-based tokenizer that produces compact semantic image tokens with a dual role in flow matching: providing a data-dependent reconstruction prior for initialization and a conditioning signal for flow-based refinement. By explicitly decoupling semantic representation from perceptual generation, our dual representation simplifies the flow-based learning objective, leading to more stable optimization and improved perceptual compression performance. PerCoV2 further introduces a dedicated 1D masked entropy model to improve rate efficiency and optional decoder-side multimodal enhancement via a vision-language model (Molmo) without increasing the transmitted bit budget. On MSCOCO-30k, PerCoV2 achieves state-of-the-art statistical fidelity, measured by FID and KID, across ultra-low and extreme bit-rates (0.0015-0.025 bpp). When trained solely on the general-purpose SA-1B dataset, PerCoV2 further demonstrates strong zero-shot generalization to widely adopted high-resolution benchmarks, including DIV2K and CLIC 2020, achieving competitive statistical fidelity with the current leading method, AEIC-ME. Finally, we introduce PerCoV2-distilled, a practical single-step variant derived from multi-step flow matching that accelerates decoding by 5.37x over PerCoV1, while preserving perceptual compression performance.

Related

• HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression
• ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization
• Tree-Structured Vector Quantization For Efficient And Progressive Image Compression
• LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression
• SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates

Source: arXiv cs.CV | 2026-10-06