Related papers: DVI: Disentangling Semantic and Visual Identity fo…

Speech-driven 3D facial animation aims to synthesize vivid facial animations that accurately synchronize with speech and match the unique speaking style. However, existing works primarily focus on achieving precise lip synchronization while…

Vision Transformer (ViT) has recently gained significant attention in solving computer vision (CV) problems due to its capability of extracting informative features and modeling long-range dependencies through the attention mechanism.…

Recent facial image synthesis methods have been mainly based on conditional generative models. Sketch-based conditions can effectively describe the geometry of faces, including the contours of facial components, hair structures, as well as…

Disentangled representations enable models to separate factors of variation that are shared across experimental conditions from those that are condition-specific. This separation is essential in domains such as biomedical data analysis,…

In real-world environments, AI systems often face unfamiliar scenarios without labeled data, creating a major challenge for conventional scene understanding models. The inability to generalize across unseen contexts limits the deployment of…

Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces. Despite these…

Segmentation in dense visual scenes poses significant challenges due to occlusions, background clutter, and scale variations. To address this, we introduce PerSense, an end-to-end, training-free, and model-agnostic one-shot framework for…

We introduce the novel Diffusion Visual Programmer (DVP), a neuro-symbolic image translation framework. Our proposed DVP seamlessly embeds a condition-flexible diffusion model within the GPT architecture, orchestrating a coherent sequence…

Deep supervised neural networks trained to classify objects have emerged as popular models of computation in the primate ventral stream. These models represent information with a high-dimensional distributed population code, implying that…

Various factors, such as identities, views (poses), and illuminations, are coupled in face images. Disentangling the identity and view representations is a major challenge in face recognition. Existing face recognition systems either use…

We introduce a new task called Defeasible Visual Entailment (DVE), where the goal is to allow the modification of the entailment relationship between an image premise and a text hypothesis based on an additional update. While this concept…

Open-world object counting leverages the robust text-image alignment of pre-trained vision-language models (VLMs) to enable counting of arbitrary categories in images specified by textual queries. However, widely adopted naive fine-tuning…

We present a training-free framework for style-personalized image generation that operates during inference using a scale-wise autoregressive model. Our method generates a stylized image guided by a single reference style while preserving…

Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by jointly leveraging auditory and visual information. However, existing methods often suffer from multi-source entanglement and audio-visual…

Tuning-free face personalization methods have developed along two distinct paradigms: text embedding approaches that map facial features into the text embedding space, and adapter-based methods that inject features through auxiliary…

Recently, advances in differential volumetric rendering enabled significant breakthroughs in the photo-realistic and fine-detailed reconstruction of complex 3D scenes, which is key for many virtual reality applications. However, in the…

In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot…

Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied…

The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre…

In recent years, unsupervised deep learning approaches have received significant attention to estimate the depth and visual odometry (VO) from unlabelled monocular image sequences. However, their performance is limited in challenging…