Related papers: Image-free Domain Generalization via CLIP for 3D H…
Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations are scarce as even humans cannot directly label the…
Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets. However, they often struggle with real-world hazy images due to domain shift, limiting their practical applicability. This paper…
Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained segmentation model to a new domain is required in hand…
We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks. We take an integrated approach that…
Hand pose estimation from a single image has many applications. However, approaches to full 3D body pose estimation are typically trained on day-to-day activities or actions. As such, detailed hand-to-hand interactions are poorly…
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…
The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely…
Pretrained visual-language models have demonstrated impressive zero-shot abilities in image captioning, when accompanied by hand-crafted prompts. Meanwhile, hand-crafted prompts utilize human prior knowledge to guide the model. However, due…
We propose an entirely data-driven approach to estimating the 3D pose of a hand given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a…
This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this…
Although deep learning models have shown impressive performance on supervised learning tasks, they often struggle to generalize well when the training (source) and test (target) domains differ. Unsupervised domain adaptation (DA) has…
Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks due to its generalizability and…
The Visual Language Model, known for its robust cross-modal capabilities, has been extensively applied in various computer vision tasks. In this paper, we explore the use of CLIP (Contrastive Language-Image Pretraining), a vision-language…
Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits…
Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a…
This paper addresses the 3D point cloud reconstruction and 3D pose estimation of the human hand from a single RGB image. To that end, we present a novel pipeline for local and global point cloud reconstruction using a 3D hand template while…
Image composition is a fundamental operation in image editing field. However, unharmonious foreground and background downgrade the quality of composite image. Image harmonization, which adjusts the foreground to improve the consistency, is…
Markerless tracking of hands and fingers is a promising enabler for human-computer interaction. However, adoption has been limited because of tracking inaccuracies, incomplete coverage of motions, low framerate, complex camera setups, and…
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image…
Tremendous amounts of expensive annotated data are a vital ingredient for state-of-the-art 3d hand pose estimation. Therefore, synthetic data has been popularized as annotations are automatically available. However, models trained only with…