相关论文: Rethinking the Objectives of Vector-Quantized Toke…

In this paper, we propose a multi-stage and high-resolution model for image synthesis that uses fine-grained attributes and masks as input. With a fine-grained attribute, the proposed model can detailedly constrain the features of the…

A good Text-to-Image model should not only generate high quality images, but also ensure the consistency between the text and the generated image. Previous models failed to simultaneously fix both sides well. This paper proposes a Gradual…

Vector quantization(VQ) is a lossy data compression technique from signal processing for which simple competitive learning is one standard method to quantize patterns from the input space. Extending competitive learning VQ to the domain of…

Most existing text-to-image synthesis tasks are static single-turn generation, based on pre-defined textual descriptions of images. To explore more practical and interactive real-life applications, we introduce a new task - Interactive…

Quantization has been proven to be an effective method for reducing the computing and/or storage cost of DNNs. However, the trade-off between the quantization bitwidth and final accuracy is complex and non-convex, which makes it difficult…

The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction without per-scene optimization. However, its billion-parameter scale creates high memory and compute demands, hindering on-device deployment.…

Semantic image synthesis aims to generate photo realistic images given a semantic segmentation map. Despite much recent progress, training them still requires large datasets of images annotated with per-pixel label maps that are extremely…

Manipulating latent code in generative adversarial networks (GANs) for facial image synthesis mainly focuses on continuous attribute synthesis (e.g., age, pose and emotion), while discrete attribute synthesis (like face mask and eyeglasses)…

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to…

Recent audio generation models typically rely on Variational Autoencoders (VAEs) and perform generation within the VAE latent space. Although VAEs excel at compression and reconstruction, their latents inherently encode low-level acoustic…

Synthetic tabular data emerges as an alternative for sharing knowledge while adhering to restrictive data access regulations, e.g., European General Data Protection Regulation (GDPR). Mainstream state-of-the-art tabular data synthesizers…

Continuous human motion understanding remains a core challenge in computer vision due to its high dimensionality and inherent redundancy. Efficient compression and representation are crucial for analyzing complex motion dynamics. In this…

A good metric, which promises a reliable comparison between solutions, is essential for any well-defined task. Unlike most vision tasks that have per-sample ground-truth, image synthesis tasks target generating unseen data and hence are…

Existing compression methods typically focus on the removal of signal-level redundancies, while the potential and versatility of decomposing visual data into compact conceptual components still lack further study. To this end, we propose a…

Quantum Generative Adversarial Networks (QGANs), an intersection of quantum computing and machine learning, have attracted widespread attention due to their potential advantages over classical analogs. However, in the current era of Noisy…

Unpaired image-to-image translation is the problem of mapping an image in the source domain to one in the target domain, without requiring corresponding image pairs. To ensure the translated images are realistically plausible, recent works,…

Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…

We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature…

Non-autoregressive generative transformers recently demonstrated impressive image generation performance, and orders of magnitude faster sampling than their autoregressive counterparts. However, optimal parallel sampling from the true joint…