相关论文: 3D Segmentation of Humans in Point Clouds with Syn…

Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work, we jointly address…

The 3D world limits the human body pose and the human body pose conveys information about the surrounding objects. Indeed, from a single image of a person placed in an indoor scene, we as humans are adept at resolving ambiguities of the…

Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate in the 2D image space. Direct semantic segmentation of unstructured 3D point…

Generating good quality and geometrically plausible synthetic images of humans with the ability to control appearance, pose and shape parameters, has become increasingly important for a variety of tasks ranging from photo editing, fashion…

High fidelity digital 3D environments have been proposed in recent years, however, it remains extremely challenging to automatically equip such environment with realistic human bodies. Existing work utilizes images, depth or semantic maps…

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from the part…

Recent works on dynamic 3D neural field reconstruction assume the input from synchronized multi-view videos whose poses are known. The input constraints are often not satisfied in real-world setups, making the approach impractical. We show…

Capturing and labeling real-world 3D data is laborious and time-consuming, which makes it costly to train strong 3D models. To address this issue, recent works present a simple method by generating randomized 3D scenes without simulation…

3D human generation is an important problem with a wide range of applications in computer vision and graphics. Despite recent progress in generative AI such as diffusion models or rendering methods like Neural Radiance Fields or Gaussian…

The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for on-the-fly dense…

3D human generation is increasingly significant in various applications. However, the direct use of 2D generative methods in 3D generation often results in losing local details, while methods that reconstruct geometry from generated images…

Forecasting long-term 3D human motion is challenging: the stochasticity of human behavior makes it hard to generate realistic human motion from the input sequence alone. Information on the scene environment and the motion of nearby people…

Semantic segmentation has emerged as a pivotal area of study in computer vision, offering profound implications for scene understanding and elevating human-machine interactions across various domains. While 2D semantic segmentation has…

We introduce a method to synthesize animator guided human motion across 3D scenes. Given a set of sparse (3 or 4) joint locations (such as the location of a person's hand and two feet) and a seed motion sequence in a 3D scene, our method…

The figure-ground segmentation of humans in images captured in natural environments is an outstanding open problem due to the presence of complex backgrounds, articulation, varying body proportions, partial views and viewpoint changes. In…

We are interested in automatic scene understanding from geometric cues. To this end, we aim to bring semantic segmentation in the loop of real-time reconstruction. Our semantic segmentation is built on a deep autoencoder stack trained…

Although synthetic training data has been shown to be beneficial for tasks such as human pose estimation, its use for RGB human action recognition is relatively unexplored. Our goal in this work is to answer the question whether synthetic…

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few…

Videos from edited media like movies are a useful, yet under-explored source of information. The rich variety of appearance and interactions between humans depicted over a large temporal context in these films could be a valuable source of…