Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression
Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, color shifting, and texture loss, thereby compromising perceptual quality of images. To address these issues, this study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss, to enhance the perceptual quality of image reconstructions. Additionally, we have implemented a latent refinement process to generate content-aware latent codes. These codes adhere to bit-rate constraints, balance the trade-off between distortion and fidelity, and prioritize bit allocation to regions of greater importance. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression. On CLIC2024 validation set, our approach achieves a 62% bitrate saving compared to MS-ILLM under FID metric.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CompressionMS-SSIMSSIMSimilar Papers 제목 키워드 기반
Sparse Refinement for Efficient High-Resolution Semantic Segmentation
Semantic segmentation empowers numerous real-world applications, such as autonomous driving and augmented/mixed reality. These applications often operate on high-resolution images (e.g., 8 megapixels) to capture the fine…
Autonomous DrivingMixed RealitySemantic SegmentationLatent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
Ultra-High Definition (UHD) image restoration faces a trade-off between computational efficiency and high-frequency detail retention. While Variational Autoencoders (VAEs) improve efficiency via latent-space processing, …
Computational EfficiencyImage RestorationSelf-Labeling Refinement for Robust Representation Learning with Bootstrap Your Own Latent
In this work, we have worked towards two major goals. Firstly, we have investigated the importance of Batch Normalisation (BN) layers in a non-contrastive representation learning framework called Bootstrap Your Own Laten…
Representation LearningSemantic contrastive learning for orthogonal X-ray computed tomography reconstruction
X-ray computed tomography (CT) is widely used in medical imaging, with sparse-view reconstruction offering an effective way to reduce radiation dose. However, ill-posed conditions often result in severe streak artifacts.…
Contrastive LearningSemantic SimilaritySENSE: Self-Supervised Neural Embeddings for Spatial Ensembles
Analyzing and visualizing scientific ensemble datasets with high dimensionality and complexity poses significant challenges. Dimensionality reduction techniques and autoencoders are powerful tools for extracting features…
Dimensionality Reduction