Related papers: SVGBuilder: Component-Based Colored SVG Generation…
The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and local parallel…
Recently, Vector Quantized AutoRegressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to bottom right in the latent space. Although the simple…
Perceiving vehicles in a driver's blind spot is vital for safe driving. The detection of potentially dangerous vehicles in these blind spots can benefit from vehicular network semantic communication technology. However, efficient semantic…
The integration of advanced video codecs into the streaming pipeline is growing in response to the increasing demand for high quality video content. However, the significant computational demand for advanced codecs like Versatile Video…
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video…
We introduce $\textit{InteractiveVideo}$, a user-centric framework for video generation. Different from traditional generative approaches that operate based on user-provided images or text, our framework is designed for dynamic interaction,…
3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…
Music videos, as a prevalent form of multimedia entertainment, deliver engaging audio-visual experiences to audiences and have gained immense popularity among singers and fans. Creators can express their interpretations of music naturally…
Generative models of graphs are well-known, but many existing models are limited in scalability and expressivity. We present a novel sequential graphical variational autoencoder operating directly on graphical representations of data. In…
Design-to-code generation has emerged as a promising approach to bridge the gap between design prototypes and deployable frontend code. However, existing methods often suffer from structural inconsistencies, asset misalignment, and limited…
Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely…
Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner. Here, we present a new architecture for image generators,…
Flexible user controls are desirable for content creation and image editing. A semantic map is commonly used intermediate representation for conditional image generation. Compared to the operation on raw RGB pixels, the semantic map enables…
Video compression is a critical component of Internet video delivery. Recent work has shown that deep learning techniques can rival or outperform human-designed algorithms, but these methods are significantly less compute and…
Video super-resolution (VSR) approaches have shown impressive temporal consistency in upsampled videos. However, these approaches tend to generate blurrier results than their image counterparts as they are limited in their generative…
Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic tasks essential for professional workflows. Existing methods predominantly rely on…
Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on latent computation becomes inadequate. A promising approach…
This paper presents a deep generative modeling framework for controllably synthesizing implied volatility surfaces (IVSs) using a variational autoencoder (VAE). Unlike conventional data-driven models, our approach provides explicit control…
Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…
Recent years have seen impressive advances in text-to-image generation, with image generative or unified models producing high-quality images from text. Yet these models still struggle with fine-grained color controllability, often failing…