Related papers: IMFNet: Interpretable Multimodal Fusion for Point …
Learning for manipulation requires using policies that have access to rich sensory information such as point clouds or RGB images. Point clouds efficiently capture geometric structures, making them essential for manipulation tasks in…
Self-attention modules have demonstrated remarkable capabilities in capturing long-range relationships and improving the performance of point cloud tasks. However, point cloud objects are typically characterized by complex, disordered, and…
Masked autoencoding has achieved great success for self-supervised learning in the image and language domains. However, mask based pretraining has yet to show benefits for point cloud understanding, likely due to standard backbones like…
Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…
This research presents a novel multimodal data fusion methodology for pain behavior recognition, integrating statistical correlation analysis with human-centered insights. Our approach introduces two key innovations: 1) integrating…
Robotic agents need to understand how to interact with objects in their environment, both autonomously and during human-robot interactions. Affordance detection on 3D point clouds, which identifies object regions that allow specific…
In perception, multiple sensory information is integrated to map visual information from 2D views onto 3D objects, which is beneficial for understanding in 3D environments. But in terms of a single 2D view rendered from different angles,…
Semantic pattern of an object point cloud is determined by its topological configuration of local geometries. Learning discriminative representations can be challenging due to large shape variations of point sets in local regions and…
Common deep learning models for 3D environment perception often use pillarization/voxelization methods to convert point cloud data into pillars/voxels and then process it with a 2D/3D convolutional neural network (CNN). The pioneer work…
Recent Transformer-based methods have achieved advanced performance in point cloud registration by utilizing advantages of the Transformer in order-invariance and modeling dependency to aggregate information. However, they still suffer from…
Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks. However, creating feature representation of robust, discriminative…
3D single object tracking plays a crucial role in computer vision. Mainstream methods mainly rely on point clouds to achieve geometry matching between target template and search area. However, textureless and incomplete point clouds make it…
Recently, 3D understanding research sheds light on extracting features from point cloud directly, which requires effective shape pattern description of point clouds. Inspired by the outstanding 2D shape descriptor SIFT, we design a module…
Instance segmentation is an important task for biomedical and biological image analysis. Due to the complicated background components, the high variability of object appearances, numerous overlapping objects, and ambiguous object…
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers…
Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the…
Point-based representations have consistently played a vital role in geometric data structures. Most point cloud learning and processing methods typically leverage the unordered and unconstrained nature to represent the underlying geometry…
Recent advances in 4D imaging radar have enabled robust perception in adverse weather, while camera sensors provide dense semantic information. Fusing the these complementary modalities has great potential for cost-effective 3D perception.…
Object detection has been extensively utilized in autonomous systems in recent years, encompassing both 2D and 3D object detection. Recent research in this field has primarily centered around multimodal approaches for addressing this…
3D object detection has become indispensable in the field of autonomous driving. To date, gratifying breakthroughs have been recorded in 3D object detection research, attributed to deep learning. However, deep learning algorithms are…