Related papers: HoloPart: Generative 3D Part Amodal Segmentation

Amodal panoptic segmentation aims to connect the perception of the world to its cognitive understanding. It entails simultaneously predicting the semantic labels of visible scene regions and the entire shape of traffic participant…

Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part…

To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…

Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. In this paper, we propose a novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addresses this problem by…

Text- or image-to-3D generators and 3D scanners can now produce 3D assets with high-quality shapes and textures. These assets typically consist of a single, fused representation, like an implicit neural field, a Gaussian mixture, or a mesh,…

Open-vocabulary 3D segmentation enables exploration of 3D spaces using free-form text descriptions. Existing methods for open-vocabulary 3D instance segmentation primarily focus on identifying object-level instances but struggle with…

Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view…

Superior human pose and shape reconstruction from monocular images depends on removing the ambiguities caused by occlusions and shape variance. Recent works succeed in regression-based methods which estimate parametric models directly…

Unsupervised 3D instance segmentation aims to segment objects from a 3D point cloud without any annotations. Existing methods face the challenge of either too loose or too tight clustering, leading to under-segmentation or…

Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…

Manipulating articulated objects with robotic arms is challenging due to the complex kinematic structure, which requires precise part segmentation for efficient manipulation. In this work, we introduce a novel superpoint-based perception…

Open-world 3D part segmentation is pivotal in diverse applications such as robotics and AR/VR. Traditional supervised methods often grapple with limited 3D data availability and struggle to generalize to unseen object categories. PartSLIP,…

Open-vocabulary 3D segmentation is a fundamental yet challenging task, requiring a mutual understanding of both segmentation and language. However, existing Gaussian-splatting-based methods rely either on a single 3D language field, leading…

The increasing availability of digital 3D environments, whether through image-based 3D reconstruction, generation, or scans obtained by robots, is driving innovation across various applications. These come with a significant demand for 3D…

Open-vocabulary semantic segmentation enables models to recognize and segment objects from arbitrary natural language descriptions, offering the flexibility to handle novel, fine-grained, or functionally defined categories beyond fixed…

3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D…

3D part segmentation is still an open problem in the field of 3D vision and AR/VR. Due to limited 3D labeled data, traditional supervised segmentation methods fall short in generalizing to unseen shapes and categories. Recently, the…

Deep learning has achieved remarkable results in 3D shape analysis by learning global shape features from the pixel-level over multiple views. Previous methods, however, compute low-level features for entire views without considering…

Scanning real-life scenes with modern registration devices typically give incomplete point cloud representations, mostly due to the limitations of the scanning process and 3D occlusions. Therefore, completing such partial representations…

Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. Although much effort has been devoted to removing occlusions from face images, the varying shapes and textures of occlusions…