相关论文: StyleDecoupler: Generalizable Artistic Style Disen…
A crucial problem in learning disentangled image representations is controlling the degree of disentanglement during image editing, while preserving the identity of objects. In this work, we propose a simple yet effective model with the…
This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation…
Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images. In this paper, we present ArtWeaver, a novel framework that leverages pretrained Stable Diffusion (SD) to address challenges such…
Generating photos satisfying multiple constraints find broad utility in the content creation industry. A key hurdle to accomplishing this task is the need for paired data consisting of all modalities (i.e., constraints) and their…
Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we…
Gram-based and patch-based approaches are two important research lines of style transfer. Recent diversified Gram-based methods have been able to produce multiple and diverse stylized outputs for the same content and style images. However,…
Individuals have unique facial expression and head pose styles that reflect their personalized speaking styles. Existing one-shot talking head methods cannot capture such personalized characteristics and therefore fail to produce diverse…
Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles.…
Recent research on representation learning has proved the merits of multi-modal clues for robust semantic segmentation. Nevertheless, a flexible pretrain-and-finetune pipeline for multiple visual modalities remains unexplored. In this…
In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentangled World Model to address the challenge of achieving a common goal of multiple agents interacting…
In computer vision, visual arts are often studied from a purely aesthetics perspective, mostly by analysing the visual appearance of an artistic reproduction to infer its style, its author, or its representative features. In this work,…
We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with…
We deal with the problem of learning the underlying disentangled latent factors that are shared between the paired bi-modal data in cross-modal retrieval. Our assumption is that the data in both modalities are complex, structured, and high…
With the proliferation of social media posts in recent years, the need to detect sentiments in multimodal (image-text) content has grown rapidly. Since posts are user-generated, the image and text from the same post can express different or…
When we experience a visual stimulus as beautiful, how much of that experience derives from perceptual computations we cannot describe versus conceptual knowledge we can readily translate into natural language? Disentangling perception from…
Music-to-visual style transfer is a challenging yet important cross-modal learning problem in the practice of creativity. Its major difference from the traditional image style transfer problem is that the style information is provided by…
The versatility of diffusion models in generating customized images has led to unauthorized usage of personal artwork, which poses a significant threat to the intellectual property of artists. Existing approaches relying on embedding…
Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…
Current image-to-image translations do not control the output domain beyond the classes used during training, nor do they interpolate between different domains well, leading to implausible results. This limitation largely arises because…
Knowledge distillation is a widely used paradigm for inheriting information from a complicated teacher network to a compact student network and maintaining the strong performance. Different from image classification, object detectors are…