Related papers: Rethinking the Objectives of Vector-Quantized Toke…
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…
As generative technologies advance, visual content has evolved into a complex mix of natural and AI-generated images, driving the need for more efficient coding techniques that prioritize perceptual quality. Traditional codecs and learned…
This work addresses the problems of semantic segmentation and image super-resolution by jointly considering the performance of both in training a Generative Adversarial Network (GAN). We propose a novel architecture and domain-specific…
Visual generative and understanding models typically rely on distinct tokenizers to process images, presenting a key challenge for unifying them within a single framework. Recent studies attempt to address this by connecting the training of…
The field of image generation is currently bifurcated into autoregressive (AR) models operating on discrete tokens and diffusion models utilizing continuous latents. This divide, rooted in the distinction between VQ-VAEs and VAEs, hinders…
Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training paradigms independently optimize understanding via sparse text signals and…
In recent years generative models of visual data have made a great progress, and now they are able to produce images of high quality and diversity. In this work we study representations learnt by a GAN generator. First, we show that these…
Machine learning can be used as a systematic method to non-algorithmically program quantum computers. Quantum machine learning enables us to perform computations without breaking down an algorithm into its gate building blocks, eliminating…
Recent studies have shown that StyleGANs provide promising prior models for downstream tasks on image synthesis and editing. However, since the latent codes of StyleGANs are designed to control global styles, it is hard to achieve a…
Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…
Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented…
In virtual reality (VR) applications, 360-degree images play a pivotal role in crafting immersive experiences and offering panoramic views, thus improving user Quality of Experience (QoE). However, the voluminous data generated by…
In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes. Following the two-step (layout-image) generation process, a novel…
Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers, in order to accelerate inference and reduce computation. Quantizing a model without access to the original data, zero-shot…
Recently, generative speech enhancement has garnered considerable interest; however, existing approaches are hindered by excessive complexity, limited efficiency, and suboptimal speech quality. To overcome these challenges, this paper…
We present SemanticNVS, a camera-conditioned multi-view diffusion model for novel view synthesis (NVS), which improves generation quality and consistency by integrating pre-trained semantic feature extractors. Existing NVS methods perform…
Recent advances in visually-induced audio generation are based on sampling short, low-fidelity, and one-class sounds. Moreover, sampling 1 second of audio from the state-of-the-art model takes minutes on a high-end GPU. In this work, we…
In this paper, we introduce Neural Mapper for Vector Quantized Time Series Generator (NM-VQTSG), a novel method aimed at addressing fidelity challenges in vector quantized (VQ) time series generation. VQ-based methods, such as TimeVQVAE,…
Image enhancement models for mobile devices often struggle to balance high output quality with the fast processing speeds required by mobile hardware. While recent deep learning models can enhance low-quality mobile photos into high-quality…
The advance of Generative Adversarial Networks (GANs) enables realistic face image synthesis. However, synthesizing face images that preserve facial identity as well as have high diversity within each identity remains challenging. To…