相关论文: Deformable One-shot Face Stylization via DINO Sema…

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate…

Driven by the emergence of Controllable Video Diffusion, existing Sim2Real methods for autonomous driving video generation typically rely on explicit intermediate representations to bridge the domain gap. However, these modalities face a…

In this paper, we present our framework for neural face/head reenactment whose goal is to transfer the 3D head orientation and expression of a target face to a source face. Previous methods focus on learning embedding networks for identity…

Self-supervised learning has emerged as a powerful paradigm for training deep neural networks, particularly in medical imaging where labeled data is scarce. While current approaches typically rely on synthetic augmentations of single…

For few-shot learning, it is still a critical challenge to realize photo-realistic face visually dubbing on high-resolution videos. Previous works fail to generate high-fidelity dubbing results. To address the above problem, this paper…

The DINO family of self-supervised vision models has shown remarkable transferability, yet effectively adapting their representations for segmentation remains challenging. Existing approaches often rely on heavy decoders with multi-scale…

Learning-based monocular visual odometry (VO) poses robustness, generalization, and efficiency challenges in robotics. Recent advances in visual foundation models, such as DINOv2, have improved robustness and generalization in various…

In this paper, we present a comparative analysis of various self-supervised Vision Transformers (ViTs), focusing on their local representative power. Inspired by large language models, we examine the abilities of ViTs to perform various…

Recent advances in text-to-image generation have driven interest in generating personalized human images that depict specific identities from reference images. Although existing methods achieve high-fidelity identity preservation, they are…

Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse…

In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this…

In this work, we propose a disentangled latent optimization-based method for parameterizing grouped deforming 3D objects into shape and deformation factors in an unsupervised manner. Our approach involves the joint optimization of a…

Unlike current deep keypoint detectors that are trained to recognize limited number of body parts, few-shot keypoint detection (FSKD) attempts to localize any keypoints, including novel or base keypoints, depending on the reference samples.…

We present a deep learning-based framework for portrait reenactment from a single picture of a target (one-shot) and a video of a driving subject. Existing facial reenactment methods suffer from identity mismatch and produce inconsistent…

While GAN-based models have been successful in image stylization tasks, they often struggle with structure preservation while stylizing a wide range of input images. Recently, diffusion models have been adopted for image stylization but…

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…

Among the array of neural network architectures, the Vision Transformer (ViT) stands out as a prominent choice, acclaimed for its exceptional expressiveness and consistent high performance in various vision applications. Recently, the…

Transferring the pose of a reference avatar to stylized 3D characters of various shapes is a fundamental task in computer graphics. Existing methods either require the stylized characters to be rigged, or they use the stylized character in…

Face anti-spoofing techniques based on domain generalization have recently been studied widely. Adversarial learning and meta-learning techniques have been adopted to learn domain-invariant representations. However, prior approaches often…

Self-supervised pre-training strategies have recently shown impressive results for training general-purpose feature extraction backbones in computer vision. In combination with the Vision Transformer architecture, the DINO self-distillation…