H3-Mapping: Quasi-Heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation

In recent years, implicit online dense mapping methods have achieved high-quality reconstruction results, showcasing great potential in robotics, AR/VR, and digital twins applications. However, existing methods struggle with slow texture modeling which limits their real-time performance. To address these limitations, we propose a NeRF-based dense mapping method that enables faster and higher-quality reconstruction. To improve texture modeling, we introduce quasi-heterogeneous feature grids, which inherit the fast querying ability of uniform feature grids while adapting to varying levels of texture complexity. Besides, we present a gradient-aided coverage-maximizing strategy for keyframe selection that enables the selected keyframes to exhibit a closer focus on rich-textured regions and a broader scope for weak-textured areas. Experimental results demonstrate that our method surpasses existing NeRF-based approaches in texture fidelity, geometry accuracy, and time consumption. The code for our method will be available at: https://github.com/SYSU-STAR/H3-Mapping.

Star-Searcher: A Complete and Efficient Aerial System for Autonomous Target Search in Complex Unknown Environments

This paper tackles the challenge of autonomous target search using unmanned aerial vehicles (UAVs) in complex unknown environments. To fill the gap in systematic approaches for this task, we introduce Star-Searcher, an aerial system featuring specialized sensor suites, mapping, and planning modules to optimize searching. Path planning challenges due to increased inspection requirements are addressed through a hierarchical planner with a visibility-based viewpoint clustering method. This simplifies planning by breaking it into global and local sub-problems, ensuring efficient global and local path coverage in real-time. Furthermore, our global path planning employs a history-aware mechanism to reduce motion inconsistency from frequent map changes, significantly enhancing search efficiency. We conduct comparisons with state-of-the-art methods in both simulation and the real world, demonstrating shorter flight paths, reduced time, and higher target search completeness. Our approach will be open-sourced for community benefit at https://github.com/SYSU-STAR/STAR-Searcher.

Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?

According to the Stimulus Organism Response (SOR) theory, all human behavioral reactions are stimulated by context, where people will process the received stimulus and produce an appropriate reaction. This implies that in a specific context for a given input stimulus, a person can react differently according to their internal state and other contextual factors. Analogously, in dyadic interactions, humans communicate using verbal and nonverbal cues, where a broad spectrum of listeners' non-verbal reactions might be appropriate for responding to a specific speaker behaviour. There already exists a body of work that investigated the problem of automatically generating an appropriate reaction for a given input. However, none attempted to automatically generate multiple appropriate reactions in the context of dyadic interactions and evaluate the appropriateness of those reactions using objective measures. This paper starts by defining the facial Multiple Appropriate Reaction Generation (fMARG) task for the first time in the literature and proposes a new set of objective evaluation metrics to evaluate the appropriateness of the generated reactions. The paper subsequently introduces a framework to predict, generate, and evaluate multiple appropriate facial reactions.

Collaborative Remote Control of Unmanned Ground Vehicles in Virtual Reality

Virtual reality (VR) technology is commonly used in entertainment applications; however, it has also been deployed in practical applications in more serious aspects of our lives, such as safety. To support people working in dangerous industries, VR can ensure operators manipulate standardized tasks and work collaboratively to deal with potential risks. Surprisingly, little research has focused on how people can collaboratively work in VR environments. Few studies have paid attention to the cognitive load of operators in their collaborative tasks. Once task demands become complex, many researchers focus on optimizing the design of the interaction interfaces to reduce the cognitive load on the operator. That approach could be of merit; however, it can actually subject operators to a more significant cognitive load and potentially more errors and a failure of collaboration. In this paper, we propose a new collaborative VR system to support two teleoperators working in the VR environment to remote control an uncrewed ground vehicle. We use a compared experiment to evaluate the collaborative VR systems, focusing on the time spent on tasks and the total number of operations. Our results show that the total number of processes and the cognitive load during operations were significantly lower in the two-person group than in the single-person group. Our study sheds light on designing VR systems to support collaborative work with respect to the flow of work of teleoperators instead of simply optimizing the design outcomes.

Self-supervised Video-centralised Transformer for Video Face Clustering

This paper presents a novel method for face clustering in videos using a video-centralised transformer. Previous works often employed contrastive learning to learn frame-level representation and used average pooling to aggregate the features along the temporal dimension. This approach may not fully capture the complicated video dynamics. In addition, despite the recent progress in video-based contrastive learning, few have attempted to learn a self-supervised clustering-friendly face representation that benefits the video face clustering task. To overcome these limitations, our method employs a transformer to directly learn video-level representations that can better reflect the temporally-varying property of faces in videos, while we also propose a video-centralised self-supervised framework to train the transformer model. We also investigate face clustering in egocentric videos, a fast-emerging field that has not been studied yet in works related to face clustering. To this end, we present and release the first large-scale egocentric video face clustering dataset named EasyCom-Clustering. We evaluate our proposed method on both the widely used Big Bang Theory (BBT) dataset and the new EasyCom-Clustering dataset. Results show the performance of our video-centralised transformer has surpassed all previous state-of-the-art methods on both benchmarks, exhibiting a self-attentive understanding of face videos.

DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction

In this paper, a novel learning-based network, named DeepDT, is proposed to reconstruct the surface from Delaunay triangulation of point cloud. DeepDT learns to predict inside/outside labels of Delaunay tetrahedrons directly from a point cloud and corresponding Delaunay triangulation. The local geometry features are first extracted from the input point cloud and aggregated into a graph deriving from the Delaunay triangulation. Then a graph filtering is applied on the aggregated features in order to add structural regularization to the label prediction of tetrahedrons. Due to the complicated spatial relations between tetrahedrons and the triangles, it is impossible to directly generate ground truth labels of tetrahedrons from ground truth surface. Therefore, we propose a multilabel supervision strategy which votes for the label of a tetrahedron with labels of sampling locations inside it. The proposed DeepDT can maintain abundant geometry details without generating overly complex surfaces , especially for inner surfaces of open scenes. Meanwhile, the generalization ability and time consumption of the proposed method is acceptable and competitive compared with the state-of-the-art methods. Experiments demonstrate the superior performance of the proposed DeepDT.

TSRNet: Scalable 3D Surface Reconstruction Network for Point Clouds using Tangent Convolution

Existing learning-based surface reconstruction methods from point clouds are still facing challenges in terms of scalability and preservation of details on point clouds of large scales. In this paper, we propose the TSRNet, a novel scalable learning-based method for surface reconstruction. It first takes a point cloud and its related octree vertices as input and learns to classify whether the octree vertices are in front or at back of the implicit surface. Then the Marching Cubes (MC) is applied to extract a surface from the binary labeled octree. In our method, we design a scalable learning-based pipeline for surface reconstruction. It does not consider the whole input data at once. It allows to divide the point cloud and octree vertices and to process different parts in parallel. Our network captures local geometry details by constructing local geometry-aware features for octree vertices. The local geometry-aware features enhance the predication accuracy greatly for the relative position among the vertices and the implicit surface. They also boost the generalization capability of our network. Our method is able to reconstruct local geometry details from point clouds of different scales, especially for point clouds with millions of points. More importantly, the time consumption on such point clouds is acceptable and competitive. Experiments show that our method achieves a significant breakthrough in scalability and quality compared with state-of-the-art learning-based methods.

Unsupervised Typography Transfer

Traditional methods in Chinese typography synthesis view characters as an assembly of radicals and strokes, but they rely on manual definition of the key points, which is still time-costing. Some recent work on computer vision proposes a brand new approach: to treat every Chinese character as an independent and inseparable image, so the pre-processing and post-processing of each character can be avoided. Then with a combination of a transfer network and a discriminating network, one typography can be well transferred to another. Despite the quite satisfying performance of the model, the training process requires to be supervised, which means in the training data each character in the source domain and the target domain needs to be perfectly paired. Sometimes the pairing is time-costing, and sometimes there is no perfect pairing, such as the pairing between traditional Chinese and simplified Chinese characters. In this paper, we proposed an unsupervised typography transfer method which doesn't need pairing.