Research map / Image generation / Image restoration
Bound-Conditioned Latent Inference for Progressive Image Compression
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes bound-conditioned latent inference (BLI) for progressive image compression, using decoded trit-plane prefixes as interval constraints on continuous latents rather than discrete symbols for probability prediction.
Problem
Progressive image compression must reconstruct images from prefixes of a single bitstream, requiring sequential latent inference under partial observations; existing trit-plane codecs treat decoded trits as discrete symbols and do not exploit their role as interval constraints on continuous latents.
Approach
Treat decoded trit-planes as interval bounds on the underlying continuous latents and condition latent inference/probability modeling on these bounds, instead of modeling trits only as discrete symbols.
Experimental setup
Baselines: trit-plane codecs
Builds on: trit-plane progressive codecs
Closest papers by meaning
- Robustly overfitting latents for flexible neural image compression (NeurIPS 2024 · similarity 0.89)
- Progressive Compression with Universally Quantized Diffusion Models (ICLR 2025 · similarity 0.88)
- Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression (AAAI 2025 · similarity 0.87)
- OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates (NeurIPS 2025 · similarity 0.87)
- Test-time Adaptation for Image Compression with Distribution Regularization (ICLR 2025 · similarity 0.87)
- Generative Latent Coding for Ultra-Low Bitrate Image Compression (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.