Related papers: Generative Latent Coding for Ultra-Low Bitrate Ima…

Generative learned image compression methods using Vector Quantization (VQ) have recently shown impressive potential in balancing distortion and perceptual quality. However, these methods typically estimate the entropy of VQ indices using a…

We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer…

Computational reconstruction plays a vital role in computer vision and computational photography. Most of the conventional optimization and deep learning techniques explore local information for reconstruction. Recently, nonlocal low-rank…

In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior…

We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from the perspective that…

Neural image compression methods have seen increasingly strong performance in recent years. However, they suffer orders of magnitude higher computational complexity compared to traditional codecs, which hinders their real-world deployment.…

Autoencoder-based structures have dominated recent learned image compression methods. However, the inherent information loss associated with autoencoders limits their rate-distortion performance at high bit rates and restricts their…

Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representation. However, their limited controllability and…

We show that pre-trained Generative Adversarial Networks (GANs) such as StyleGAN and BigGAN can be used as a latent bank to improve the performance of image super-resolution. While most existing perceptual-oriented approaches attempt to…

Generative face video coding (GFVC) is vital for modern applications like video conferencing, yet existing methods primarily focus on video motion while neglecting the significant bitrate contribution of audio. Despite the well-established…

At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means. We propose Generative Video Codebook Codec (GVCC), a zero-shot framework in…

Neural image codecs achieve higher compression ratios than traditional hand-crafted methods such as PNG or JPEG-XL, but often incur substantial computational overhead, limiting their deployment on energy-constrained devices such as…

Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their…

We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the "temporal" evolution in generative image compression. Specifically, we define an explicit intermediate state during decoding: a compact anchor…

Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versatile Video Coding (VVC) in both PSNR and MS-SSIM metrics. Two…

Realistic hyperspectral image (HSI) super-resolution (SR) techniques aim to generate a high-resolution (HR) HSI with higher spectral and spatial fidelity from its low-resolution (LR) counterpart. The generative adversarial network (GAN) has…

This paper proposes the decision tree latent controller generative adversarial network (DTLC-GAN), an extension of a GAN that can learn hierarchically interpretable representations without relying on detailed supervision. To impose a…

Existing mezzanine image codecs lack specialized screen content coding tools and therefore struggle to maintain high image quality under bandwidth constraints, especially in areas with dense text. Although distribution codecs offer advanced…

Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art rate-distortion (R-D) performance has been achieved by context-adaptive entropy coding approaches in which hyperprior and…

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this…