Related papers: Real-time 3D Facial Tracking via Cascaded Composit…
Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping. The popular method of fusing depth information into a truncated signed distance function (TSDF)…
Neural implicit representations have recently demonstrated compelling results on dense Simultaneous Localization And Mapping (SLAM) but suffer from the accumulation of errors in camera tracking and distortion in the reconstruction.…
Covalent organic frameworks (COFs) are promising adsorbents for gas adsorption and separation, while identifying the optimal structures among their vast design space requires efficient high-throughput screening. Conventional…
3D Gaussian Splatting (3DGS) has demonstrated impressive performance in scene reconstruction. However, most existing GS-based surface reconstruction methods focus on 3D objects or limited scenes. Directly applying these methods to…
LiDAR-camera fusion methods have shown impressive performance in 3D object detection. Recent advanced multi-modal methods mainly perform global fusion, where image features and point cloud features are fused across the whole scene. Such…
In recent advances of deep generative models, face reenactment -manipulating and controlling human face, including their head movement-has drawn much attention for its wide range of applicability. Despite its strong expressiveness, it is…
The recovery of 3D human mesh from monocular images has significantly been developed in recent years. However, existing models usually ignore spatial and temporal information, which might lead to mesh and image misalignment and temporal…
The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames. Standard motion estimators used in tracking, e.g., Long Short Term Memory (LSTM), only deal with single…
High-fidelity reconstruction of 3D human avatars has a wild application in visual reality. In this paper, we introduce FAGhead, a method that enables fully controllable human portraits from monocular videos. We explicit the traditional 3D…
Robotic manipulation requires accurate perception of the environment, which poses a significant challenge due to its inherent complexity and constantly changing nature. In this context, RGB image and point-cloud observations are two…
Multimodal image alignment involves finding spatial correspondences between volumes varying in appearance and structure. Automated alignment methods are often based on local optimization that can be highly sensitive to their initialization.…
Visual perception plays a pivotal role in enabling autonomous behavior, offering a cost-effective and efficient alternative to complex multi-sensor systems. However, robust segmentation remains a challenge in complex scenarios. To address…
Human action video recognition has recently attracted more attention in applications such as video security and sports posture correction. Popular solutions, including graph convolutional networks (GCNs) that model the human skeleton as a…
Video content is multifaceted, consisting of objects, scenes, interactions or actions. The existing datasets mostly label only one of the facets for model training, resulting in the video representation that biases to only one facet…
A long-standing goal in scene understanding is to obtain interpretable and editable representations that can be directly constructed from a raw monocular RGB-D video, without requiring specialized hardware setup or priors. The problem is…
Most existing monocular 3D pose estimation approaches only focus on a single body part, neglecting the fact that the essential nuance of human motion is conveyed through a concert of subtle movements of face, hands, and body. In this paper,…
Despite tremendous recent progress in human video generation, generative video diffusion models still struggle to capture the dynamics and physics of human motions faithfully. In this paper, we propose a new framework for human video…
We introduce the Deformable Gaussian Splats Large Reconstruction Model (DGS-LRM), the first feed-forward method predicting deformable 3D Gaussian splats from a monocular posed video of any dynamic scene. Feed-forward scene reconstruction…
We propose a novel landmarks-assisted collaborative end-to-end deep framework for automatic 4D FER. Using 4D face scan data, we calculate its various geometrical images, and afterwards use rank pooling to generate their dynamic images…
Estimating the 3D trajectory of every pixel from a monocular video is crucial and promising for a comprehensive understanding of the 3D dynamics of videos. Recent monocular 3D tracking works demonstrate impressive performance, but are…