REVIEW 46 cited by
End-to-end Optimized Image Compression
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear filters and nonlinear activation functions. Unlike most convolutional neural networks, the joint nonlinearity is chosen to implement a form of local gain control, inspired by those used to model biological neurons. Using a variant of stochastic gradient descent, we jointly optimize the entire model for rate-distortion performance over a database of training images, introducing a continuous proxy for the discontinuous loss function arising from the quantizer. Under certain conditions, the relaxed loss function may be interpreted as the log likelihood of a generative model, as implemented by a variational autoencoder. Unlike these models, however, the compression model must operate at any given point along the rate-distortion curve, as specified by a trade-off parameter. Across an independent set of test images, we find that the optimized method generally exhibits better rate-distortion performance than the standard JPEG and JPEG 2000 compression methods. More importantly, we observe a dramatic improvement in visual quality for all images at all bit rates, which is supported by objective quality estimates using MS-SSIM.
Forward citations
Cited by 46 Pith papers
-
End-to-end image compression and reconstruction with ultrahigh speed and ultralow energy enabled by opto-electronic computing processor
An integrated optoelectronic processor with a programmable 32x32 photonic matrix performs end-to-end image compression and reconstruction at 49.5 ps/pixel and 10.58 nJ/pixel, according to the authors.
-
Compress-Align-Detect: onboard change detection from unregistered images
A single neural network performs compression, co-registration, and change detection onboard a satellite, achieving F1 up to about 70% at low bitrates on simulated unregistered image pairs.
-
Towards a Universal Image Degradation Model via Content-Degradation Disentanglement
A universal image degradation model that disentangles homogeneous and inhomogeneous degradation from image content and transfers it to new images, enabling blind restoration without user-provided degradation parameters.
-
Learning Switchable Priors for Neural Image Compression
A finite set of trainable priors, selected by predicted indices, decouples entropy coding complexity from the probabilistic model family in neural image compression, enabling faster and lighter codecs that still beat BPG.
-
Hardware-Aware Deployment of Joint SAR Compression and Despeckling on FPGA
A joint SAR despeckling and compression model was deployed on an FPGA, where hardware-friendly changes like ReLU instead of GDN improved performance, residual blocks were not worth their 10x compute cost, and the FPGA...
-
Locality-Aware Density Control for Efficient Gaussian-based Image Representation
A locality-aware density-control framework for 2D Gaussian image representation that densifies coherent high-error regions and merges redundant similar Gaussians, improving PSNR at fixed budgets.
-
-8 dB SNR + 90% Packet Loss: MamVSC -- CSI-Guided Semantic Mamba for Extreme-Robust Video Semantic Communication
A Mamba-based semantic video communication system with CSI-guided adaptive encoding and packet loss recovery achieves PSNR > 21 dB at -8 dB SNR and 90% packet loss in AWGN channels.
-
HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression
A hyperprior predicts a Gaussian in codebook space and converts it to index probabilities, enabling content-adaptive entropy coding for VQ image compression.
-
SA-OOSC: A Multimodal LLM-Distilled Semantic Communication Framework for Enhanced Coding Efficiency with Scenario Understanding
A semantic communication framework uses MLLM-derived scenario-aware importance labels to allocate coding resources, improving PSNR of important image regions at comparable or lower bandwidth than prior JSCC systems.
-
JPEG Processing Neural Operator for Backward-Compatible Coding
JPNeO improves JPEG compression with neural operators at encoding and decoding, without changing the JPEG bitstream format.
-
Semantics versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification
A de-identification framework that blocks identity-related image regions and replaces them with identity-free medical semantic features, enabling adjustable privacy while preserving diagnostic utility.
-
LINR-PCGC: Lossless Implicit Neural Representations for Point Cloud Geometry Compression
A lossless point cloud geometry codec overfits a small sparse-convolution network per group of frames and entropy-codes octree occupancy using the network's predicted probabilities.
-
CosmoFlow: Scale-Aware Representation Learning for Cosmology with Flow Matching
Flow matching on CDM fields yields an 8 number latent that reconstructs fields and estimates Omega_m and sigma_8 nearly as well as a raw-field network, with channels tied to spatial scales.
-
StableCodec: Taming One-Step Diffusion for Extreme Image Compression
A one-step diffusion codec that compresses noisy latents at 64x and decodes with a single denoising step, setting state-of-the-art FID, KID, and DISTS at ultra-low bitrates.
-
End-to-End RGB-IR Joint Image Compression With Channel-wise Cross-modality Entropy Model
A channel-wise cross-modality entropy model with low-frequency context fusion improves joint RGB-IR image compression, achieving 23.1% bit rate savings over the previous state of the art on LLVIP.
-
Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution
A single rate-variable generative compression model treats quantization as a forward corruption and reverses it with a two-step denoiser, outperforming prior generative codecs on perceptual quality benchmarks.
-
Neural Video Compression with Context Modulation
DCMVC modulates the propagated temporal context with an additional oriented context from the reference frame, reporting 10.1 percent bitrate savings over DCVC-FM and 22.7 percent over VVC on standard test sets.
-
4DGS-CC: A Contextual Coding Framework for 4D Gaussian Splatting Data Compression
4DGS-CC compresses 4D Gaussian Splatting data by about 12x with maintained rendering quality by entropy-coding quantized neural voxels and a vector-quantized codebook.
-
LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks
LimitNet is a 15K-parameter progressive, content-aware image codec for MCUs that prioritizes saliency-scored latent data during offloading, improving partial-data classification accuracy over JPEG, ProgJPEG, and Starfish.
-
A Turing Test for Artificial Nets devoted to model Human Vision
A new low-level psychophysics benchmark, the Decalogue, is introduced and applied to three vision models, ranking the parametric BioMultiLayer model as closest to human behavior.
-
S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression
Channel aggregation by feed-forward networks, not spatial attention, drives rate-distortion performance in transformer-based learned image compression, and simplified models achieve state-of-the-art results with over ...
-
Towards Loss-Resilient Image Coding for Unstable Satellite Networks
A loss-resilient learned image codec using spatial-channel rearrangement, mask-conditional decoding, and Gilbert-Elliot loss simulation beats prior progressive codecs under satellite packet loss.
-
Exploiting Latent Properties to Optimize Neural Codecs
Using uniform lattice grids for quantization and entropy-gradient latent shifting improves rate-distortion performance of off-the-shelf neural codecs by 1-3% without retraining.
-
AsymLLIC: Asymmetric Lightweight Learned Image Compression
AsymLLIC uses a two-stage training scheme to replace complex decoder modules with simpler ones, cutting decoder MACs to 51.47 GMACs while keeping RD performance close to VVC.
-
Point Cloud-Assisted Neural Image Compression
Point cloud depth projected onto the image, fused through a new attention module, improves learned image compression on KITTI by 54.5% BD-rate over Cheng2020.
-
Energy-Constrained Information Storage on Memristive Devices in the Presence of Resistive Drift
Delay-conditioned deep joint source-channel coding improves energy-constrained image storage on simulated memristors subject to resistive drift.
-
An End-to-End Real-World Camera Imaging Pipeline
A single end-to-end neural network performs RAW-to-RGB conversion and image compression jointly, reporting rate-distortion gains over separate ISP-plus-codec baselines.
-
Efficient Progressive Image Compression with Variance-aware Masking
A progressive image codec that ranks residual latent elements by predicted standard deviation and transmits them from most to least important, matching state-of-the-art RD with far lower decode cost.
-
Neural Image Compression and Explanation
NICE trains a stochastic binary mask that marks decision-relevant pixels and turns the rest into a low-resolution background, giving both an explanation and about 1.6x PNG compression with a small accuracy drop.
-
Rethink Before You Execute: Adaptive Execution for World Action Models
TempoWAM adapts the replanning frequency of world action models based on an online estimate of task progress, reducing inference calls on easy tasks and improving success on hard tasks.
-
SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates
A diffusion-based image codec guided by text, a highly compressed image, and CLIP-derived semantic pseudo-words improves semantic consistency at bitrates below 0.05 bpp.
-
RAVQ-HoloNet: Rate-Adaptive Vector-Quantized Hologram Compression
RAVQ-HoloNet compresses phase-only holograms with a hierarchical VQ-VAE whose codebook size is shrunk by an LSTM module, enabling multiple bitrates from one model and claiming BD-Rate -33.91% vs DPRC.
-
Efficient Learned Image Compression Through Knowledge Distillation
Knowledge-distilled students with 64 or more channels match the rate-distortion performance of a 128-channel teacher while cutting memory by 68% and energy by 34%.
-
Conquering High Packet-Loss Erasure: MoE Swin Transformer-Based Video Semantic Communication
MSTVSC is a packet-loss-resistant semantic video codec that recovers erased semantic elements with a 3D CNN and claims MS-SSIM above 0.6 and PSNR above 20 dB at 90% packet loss.
-
Explicit Residual-Based Scalable Image Coding for Humans and Machines
Explicitly compressing pixel or feature residuals between machine-oriented and human-oriented image codec layers improves scalable coding efficiency, with up to 29.57% BD-rate savings over ICMH-FF.
-
ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression
ABC learns the structure of a neural image compression codec jointly with a rate-distortion-complexity objective, making the codec computationally scalable across the encoder, decoder, and autoregressive context model.
-
Versatile Volumetric Medical Image Coding for Human-Machine Vision
A learned volumetric medical image codec transfers inter-slice latent features across slices so a single compressed stream supports both image reconstruction and direct organ segmentation.
-
Motion Free B-frame Coding for Neural Video Compression
A kernel-based, motion-free autoencoder for B-frame coding that synthesizes frames from two reconstructed references and an interpolated frame.
-
An Information-Theoretic Regularizer for Lossy Neural Image Compression
A regularizer that maximizes conditional source entropy gives BD-rate gains of 0.9% to 3.0% across five neural compression models, but may be equivalent to reweighting the rate term.
-
Cross-Layer Encrypted Semantic Communication Framework for Panoramic Video Transmission
A cross-layer framework integrates Deep JSCC semantic coding with encryption, CRC, LDPC, and retransmission, adapting error protection to semantic importance for panoramic video.
-
Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
A large-scale benchmark shows that JPEG AI resists most tested adversarial attacks better than other neural codecs, though its high-complexity mode is less robust than its base mode.
-
Binocular Rivalry Oriented Predictive Auto-Encoding Network for Blind Stereoscopic Image Quality Measurement
PAD-Net, a Siamese encoder-decoder with a ResNet-18 quality regressor, predicts no-reference stereoscopic image quality by modeling binocular rivalry through likelihood and prior maps, and reports state-of-the-art res...
-
Scene Perceived Image Perceptual Score (SPIPS): combining global and local perception for image quality assessment
SPIPS fuses traditional and deep features, separated into semantic and perceptual streams, to predict human-perceived image quality and reports small gains over LPIPS on BAPPS.
-
Human Perceptual Evaluations for Image Compression
Human preference judgments contradict MS-SSIM rankings: learned compression methods with higher MS-SSIM are often judged visually worse than BPG and JPEG-2000.
-
Video Quality Assessment: A Comprehensive Survey
A comprehensive survey of video quality assessment methods and databases, with benchmark comparisons of full-reference and no-reference models on UGC and AIGC datasets.
-
Point Cloud Compression and Objective Quality Assessment: A Survey
A survey of point cloud compression and objective quality assessment that benchmarks representative methods on standard datasets and distills design insights.
Discussion (0). Continue with ORCID to comment.