Related papers: MoGen: A Unified Collaborative Framework for Contr…
The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single…
Existing methods for multi-domain image-to-image translation (or generation) attempt to directly map an input image (or a random vector) to an image in one of the output domains. However, most existing methods have limited scalability and…
We propose a novel model named Multi-Channel Attention Selection Generative Adversarial Network (SelectionGAN) for guided image-to-image translation, where we translate an input image into another while respecting an external semantic…
Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we…
In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level…
Visual designers naturally draw inspiration from multiple visual references, combining diverse elements and aesthetic principles to create artwork. However, current image generative frameworks predominantly rely on single-source inputs --…
Despite rapid advancements in the capabilities of generative models, pretrained text-to-image models still struggle in capturing the semantics conveyed by complex prompts that compound multiple objects and instance-level attributes.…
While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…
Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for semantic synthesis, while others rely on localization cues…
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However, this quality comes at significant computational cost: nearly all of these models are iterative and…
Multimodality-to-Multiaudio (MM2MA) generation faces significant challenges in synthesizing diverse and contextually aligned audio types (e.g., sound effects, speech, music, and songs) from multimodal inputs (e.g., video, text, images),…
Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In…
Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour. This paper proposes the first multiple and multimodal (verbal and nonverbal)…
Medical imaging systems are commonly assessed and optimized by use of objective-measures of image quality (IQ) that quantify the performance of an observer at specific tasks. Variation in the objects to-be-imaged is an important source of…
In recent years, advancements in AIGC (Artificial Intelligence Generated Content) technology have significantly enhanced the capabilities of large text-to-image models. Despite these improvements, controllable image generation remains a…
Image translation is a burgeoning field in computer vision where the goal is to learn the mapping between an input image and an output image. However, most recent methods require multiple generators for modeling different domain mappings,…
In this work, we introduce FlexGen, a flexible framework designed to generate controllable and consistent multi-view images, conditioned on a single-view image, or a text prompt, or both. FlexGen tackles the challenges of controllable…
Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout…
Autoregressive Model (AR) has shown remarkable success in conditional image generation. However, these approaches for multiple reference generation struggle with decoupling different reference identities. In this work, we propose the…
Existing approaches for controlling text-to-image diffusion models, while powerful, do not allow for explicit 3D object-centric control, such as precise control of object orientation. In this work, we address the problem of multi-object…