Related papers: UniX: Unifying Autoregression and Diffusion for Ch…
The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted in a lack of data volume and generalizability across different motion…
The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from…
Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for…
Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results,…
Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental inconsistency: understanding favors compact embeddings, whereas…
Rendering and inverse rendering are pivotal tasks in both computer vision and graphics. The rendering equation is the core of the two tasks, as an ideal conditional distribution transfer function from intrinsic properties to RGB images.…
Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggle with achieving…
Transformer-based architectures have demonstrated remarkable success across various domains, but their deployment on edge devices remains challenging due to high memory and computational demands. In this paper, we introduce a novel Reuse…
The adoption of Artificial Intelligence in medical imaging holds great promise, yet it remains hindered by challenges such as data scarcity, privacy concerns, and the need for robust multimodal integration. While recent advances in…
Denoising diffusion models have found applications in image segmentation by generating segmented masks conditioned on images. Existing studies predominantly focus on adjusting model architecture or improving inference, such as test-time…
In practical AI workflows, complex tasks often involve chaining multiple generative models, such as using a video or 3D generation model after a 2D image generator. However, distributional mismatches between the output of upstream models…
While recent advances in large-scale foundational models show promising results, their application to the medical domain has not yet been explored in detail. In this paper, we progress into the realms of large-scale modeling in medical…
Image restoration aims to recover content from inputs degraded by various factors, such as adverse weather, blur, and noise. Perceptual Image Restoration (PIR) methods improve visual quality but often do not support downstream tasks…
With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. However, directly repurposing the generative denoising process…
Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large…
Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing a unified tokenizer. However, existing tokenizers face a…
Latent Diffusion Models have shown remarkable results in text-guided image synthesis in recent years. In the domain of natural (RGB) images, recent works have shown that such models can be adapted to various vision-language downstream tasks…
Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image- and video-language understanding. Conversely, less attention…
Recent advancements in text-to-3D generation technology have significantly advanced the conversion of textual descriptions into imaginative well-geometrical and finely textured 3D objects. Despite these developments, a prevalent limitation…
Medical Vision-Language Pretraining (MedVLP) shows promise in learning generalizable and transferable visual representations from paired and unpaired medical images and reports. MedVLP can provide useful features to downstream tasks and…