Related papers: 3SGen: Unified Subject, Style, and Structure-Drive…

GAN-based image editing task aims at manipulating image attributes in the latent space of generative models. Most of the previous 2D and 3D-aware approaches mainly focus on editing attributes in images with ambiguous semantics or regions…

Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight…

It is a big challenge of computer vision to make machine automatically describe the content of an image with a natural language sentence. Previous works have made great progress on this task, but they only use the global or local image…

We introduce Garment3DGen a new method to synthesize 3D garment assets from a base mesh given a single input image as guidance. Our proposed approach allows users to generate 3D textured clothes based on both real and synthetic images, such…

Image synthesis via Generative Adversarial Networks (GANs) of three-dimensional (3D) medical images has great potential that can be extended to many medical applications, such as, image enhancement and disease progression modeling. However,…

Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification problem rather…

In this paper, we present InSeGAN, an unsupervised 3D generative adversarial network (GAN) for segmenting (nearly) identical instances of rigid objects in depth images. Using an analysis-by-synthesis approach, we design a novel GAN…

Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I), whether instantiated as assembled unified frameworks which couple powerful vision-language model (VLM) with…

Text-to-image synthesis is the task of generating images from text descriptions. Image generation, by itself, is a challenging task. When we combine image generation and text, we bring complexity to a new level: we need to combine data from…

We propose the first practical multitask image enhancement network, that is able to learn one-to-many and many-to-one image mappings. We show that our model outperforms the current state of the art in learning a single enhancement mapping,…

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with…

Single-image 3D generation has emerged as a prominent research topic, playing a vital role in virtual reality, 3D modeling, and digital content creation. However, existing methods face challenges such as a lack of multi-view geometric…

The entertainment industry relies on 3D visual content to create immersive experiences, but traditional methods for creating textured 3D models can be time-consuming and subjective. Generative networks such as StyleGAN have advanced image…

Generating an image from a given text description has two goals: visual realism and semantic consistency. Although significant progress has been made in generating high-quality and visually realistic images using generative adversarial…

Research on 3D Vision-Language Models (3D-VLMs) is gaining increasing attention, which is crucial for developing embodied AI within 3D scenes, such as visual navigation and embodied question answering. Due to the high density of visual…

Scaling large multimodal models (LMMs) to 3D understanding poses unique challenges: point cloud data is sparse and irregular, existing models rely on fragmented architectures with modality-specific encoders, and training pipelines often…

The goal of multi-task learning is to learn to conduct multiple tasks simultaneously based on a shared data representation. While this approach can improve learning efficiency, it may also cause performance degradation due to task conflicts…

Synthetic medical image generation has a huge potential for improving healthcare through many applications, from data augmentation for training machine learning systems to preserving patient privacy. Conditional Adversarial Generative…

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…