eess.IVNov 3, 2026

Benchmarking Neural Image Compression with DCT-Based Spectral Diagnostics

Authors: Nikolay I. Kalmykov, Razan Dibo, Yujun Du, Yipeng Liu, Ivan Oseledets, Anh-Huy Phan

Organizations: Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia · University of Electronic Science and Technology of China (UESTC), Chengdu, China · AIRI, Moscow, Russia

Abstract

Neural image compression (NIC) models are commonly evaluated with scalar rate-distortion metrics, which do not show how a codec treats individual spatial frequencies. We propose a benchmark that probes codecs with the DCT basis matrix and single-frequency test images. We measure relative off-target energy (leakage), the fraction of reconstruction energy outside the probed frequency, together with target-frequency gain. Exact decompositions and bounds relate these measurements to reconstruction error. At operating points nearest 1 bpp, the BMSHJ, MBT, and Cheng2020 models leave 80-97% of their reconstructed high-band energy outside the target bin and have target-frequency gains of 0.02-0.23, whereas TCM and FTIC attain off-target energy in the classical-codec range. Both probe types identify behavior absent from scalar metrics: released Cheng2020-Anchor models produce extreme pre-clamp outputs on isolated single-frequency inputs. Finally, decoder-only fine-tuning with natural-image and leakage losses reduces basis off-target energy by 90-99.8% across all eight evaluated architectures while keeping the bitstream fixed, at a Kodak PSNR cost of 0.09-0.59 dB.

Figures & tables

Explore similar work

Nov 5, 2026

Neural Image Compression with Internal-External Prior Fusion and Alignment

Existing context models for learned image com- pression rely primarily on internal priors from the current image, overlooking common patterns and typical textures shared across natural images. To address this limitation, we propose an Internal-External Prior Fusion-Alignment (IE-PFA) context model built upon quadtree spatial-channel joint modeling, where a learnable dictionary shared by the encoder and decoder serves as an external prior. Specifically, an RWKV-based Spatial- Channel Prior Fusion (RSCPF) module efficiently fuses inter- nal and external priors along spatial and channel dimensions with linear complexity, while a training-only Self-Distilled Prior Alignment (SDPA) mechanism aligns them without inference overhead. Moreover, our model supports variable-rate coding over 64 quality levels within a single network and is accelerated by custom CUDA operators. Experiments on seven benchmarks demonstrate state-of-the-art rate-distortion performance, achiev- ing an average BD-Rate saving of 21.65% over VTM-22.0-Intra, with only 29.9M parameters and the fastest coding speed among advanced neural codecs (61 ms encoding and 52 ms decoding). Code is available at https://github.com/stcnjtech/DCVC-X-Intra.
Oct 19, 2026

PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error Compensation

Neural image codecs face a fundamental trade-off between pixel fidelity and perceptual quality. Distortion-optimized codecs preserve pixel-wise fidelity but produce blurred reconstructions at low bitrates, whereas generative codecs leverage learned priors to improve perceptual quality but tend to exhibit saturating PSNR at higher bitrates and require separate models for different bitrate targets. We propose PerQ, which reframes perceptual reconstruction as inverse generative modeling with bounded support. Specifically, we define the quantization cell as the set of latents that yield the same transmitted symbols and derive a transport bound showing that reconstructions from this cell remain within a rate-determined radius of the codec output. This motivates performing generative reconstruction within the codec-induced quantization cell, rather than sampling from an unconstrained image prior. PerQ implements this principle by attaching a rate-conditioned flow-matching compensator to a frozen, multi-rate distortion-optimized backbone, enabling perceptual enhancement while preserving the backbone's coding performance. Experiments on Kodak and CLIC2020 show that PerQ achieves perceptual performance comparable to generative codecs such as MS-ILLM in LPIPS and FID, while maintaining competitive PSNR relative to distortion-optimized codecs such as ELIC. A single model checkpoint supports a wide bitrate range with fast decoding, and the compensator provides consistent gains across three different backbones. The implementation is available at https://jasminepp.github.io/PerQ/.
Jun 11, 2026

Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimization

The rate-distortion-perception (RDP) trade-off extends classical rate--distortion theory by imposing a distributional constraint on reconstructions, providing a unified framework for neural image compression that jointly governs fidelity and perceptual realism. While prior work achieves near-optimal rate--perception trade-offs, practical frameworks explicitly realizing the full RDP surface remain scarce, primarily due to the difficulty of introducing common randomness at the decoder. We propose DCIC (Dual-Constrained Diffusion Image Compression), which integrates a learned codec with a diffusion-based decoder governed by joint distortion and idempotence constraints. The distortion constraint bounds reconstruction fidelity relative to the base codec output; the idempotence constraint -- requiring that re-encoding the restored image recovers the base codec reconstruction -- serves as a tractable surrogate for the distributional perception requirement. Together, they steer the reverse denoising process via iterative optimization with consistent noise injection, realizing common randomness without additional rate overhead. At fixed rate, dual attenuation factors (KD,KP)(K_D, K_P) jointly navigate the Pareto frontier of the distortion-perception plane, enabling continuously adjustable fidelity-realism trade-offs from a single bitstream. DCICRD_{RD} (KP=0K_P{=}0) and DCICRP_{RP} (KD=0K_D{=}0) arise as boundary curves, with DCICRDP_{RDP} (KD=KP=1K_D = K_P=1) realizing the optimal interior operating point. Experiments on CelebA-HQ, CLIC2020, and ImageNet-1K across CNN, Transformer, and hybrid architectures confirm that DCICRDP_{RDP} achieves superior BD-PSNR over all perceptual codecs, while DCICRP_{RP} matches dedicated perception-oriented methods in BD-FID, validating the practical value of full RDP surface navigation.