Related papers: Learnings from Scaling Visual Tokenizers for Recon…
This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically…
Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and…
Objective. Standard Magnetic Resonance Imaging (MRI) reconstruction pipelines discard phase information captured during acquisition, despite evidence that it encodes tissue properties relevant to tumor diagnosis. Current machine learning…
Despite the promising progress of recent autoregressive models in text-to-image (T2I) generation, their ability to handle multi-attribute and ambiguous prompts remains limited. To address these limitations, existing works have applied…
Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…
Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns from convolutional architectures. We show that this explicit image-space reconstruction is not…
Most advanced visual grounding methods rely on Transformers for visual-linguistic feature fusion. However, these Transformer-based approaches encounter a significant drawback: the computational costs escalate quadratically due to the…
Video Coding for Machines (VCM) is committed to bridging to an extent separate research tracks of video/image compression and feature compression, and attempts to optimize compactness and efficiency jointly from a unified perspective of…
Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…
Despite the success of transformers on various computer vision tasks, they suffer from excessive memory and computational cost. Some works present dynamic vision transformers to accelerate inference by pruning redundant tokens. A key to…
Vision transformers have been widely explored in various vision tasks. Due to heavy computational cost, much interest has aroused for compressing vision transformer dynamically in the aspect of tokens. Current methods mainly pay attention…
In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of…
Screenshot-to-code generation aims to translate user interface screenshots into executable frontend code that faithfully reproduces the target layout and style. Existing multimodal large language models perform this mapping directly from…
The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range…
End-to-end image and video codecs are becoming increasingly competitive, compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These trainable codecs have many advantages over…
Recent progress in generative compression technology has significantly improved the perceptual quality of compressed data. However, these advancements primarily focus on producing high-frequency details, often overlooking the ability of…
The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, processing uniform background areas of an image should not…
Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…
This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between…
Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual…