Related papers: Texture Vector-Quantization and Reconstruction Awa…
Visual Text Rendering (VTR) remains a critical challenge in text-to-image generation, where even advanced models frequently produce text with structural anomalies such as distortion, blurriness, and misalignment. However, we find that…
Anomaly Detection (AD), as a critical problem, has been widely discussed. In this paper, we specialize in one specific problem, Visual Defect Detection (VDD), in many industrial applications. And in practice, defect image samples are very…
Constructing 3D representations of object geometry is critical for many robotics tasks, particularly manipulation problems. These representations must be built from potentially noisy partial observations. In this work, we focus on the…
This work introduces Semantically Masked Vector Quantized Generative Adversarial Network (SQ-GAN), a novel approach integrating semantically driven image coding and vector quantization to optimize image compression for…
Given an incomplete image without additional constraint, image inpainting natively allows for multiple solutions as long as they appear plausible. Recently, multiplesolution inpainting methods have been proposed and shown the potential of…
In the last years, the design of image reconstruction methods in the field of quantitative Magnetic Resonance Imaging (qMRI) has experienced a paradigm shift. Often, when dealing with (quantitative) MR image reconstruction problems, one is…
High-fidelity and efficient audio-driven talking head generation has been a key research topic in computer graphics and computer vision. In this work, we study vector image based audio-driven talking head generation. Compared with directly…
Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…
Recent methods for dynamic human reconstruction have attained promising reconstruction results. Most of these methods rely only on RGB color supervision without considering explicit geometric constraints. This leads to existing human…
Methods for Visual Question Anwering (VQA) are notorious for leveraging dataset biases rather than performing reasoning, hindering generalization. It has been recently shown that better reasoning patterns emerge in attention layers of a…
Super-resolution (SR) networks have been investigated for a while, with their mobile and lightweight versions gaining noticeable popularity recently. Quantization, the procedure of decreasing the precision of network parameters (mostly FP32…
Generative models with discrete latent representations have recently demonstrated an impressive ability to learn complex high-dimensional data distributions. However, their performance relies on a long sequence of tokens per instance and a…
Generative models trained on extensive high-quality datasets effectively capture the structural and statistical properties of clean images, rendering them powerful priors for transforming degraded features into clean ones in image…
Post-training quantization (PTQ) for vision transformers (ViTs) has received increasing attention from both academic and industrial communities due to its minimal data needs and high time efficiency. However, many current methods fail to…
In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance. Recent state-of-the-art methods for neural image compression are mainly based on nonlinear transform coding…
Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical prediction. However, its progress is hindered by the misalignment…
Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these models to their low-bit counterparts without…
Consistency learning with feature perturbation is a widely used strategy in semi-supervised medical image segmentation. However, many existing perturbation methods rely on dropout, and thus require a careful manual tuning of the dropout…
Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and…
Blind text image super-resolution (SR) is challenging as one needs to cope with diverse font styles and unknown degradation. To address the problem, existing methods perform character recognition in parallel to regularize the SR task,…