12 papers
Zero-Shot Depth from Defocus
Yiming Zuo, Hongyu Wen, Venkat Subramanian +5
Depth from Defocus (DfD) is the task of estimating a dense metric depth map from a focus stack. Unlike previous works overfitting to a certain dataset, this paper focuses on the ch…
GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration
Zhixin Cheng, Jiacheng Deng, Xinjun Li +5
Image-to-point cloud registration methods typically follow a coarse-to-fine pipeline, extracting patch-level correspondences and refining them into dense pixel-to-point matches. Ho…
TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels
Jiahao Lu, Weitao Xiong, Jiacheng Deng +6
Monocular 3D tracking aims to capture the long-term motion of pixels in 3D space from a single monocular video and has witnessed rapid progress in recent years. However, we argue t…
Adaptive Agent Selection and Interaction Network for Image-to-point cloud Registration
Zhixin Cheng, Xiaotian Yin, Jiacheng Deng +5
Typical detection-free methods for image-to-point cloud registration leverage transformer-based architectures to aggregate cross-modal features and establish correspondences. Howev…
CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection
Zhixin Cheng, Jiacheng Deng, Xinjun Li +5
Detection-free methods typically follow a coarse-to-fine pipeline, extracting image and point cloud features for patch-level matching and refining dense pixel-to-point corresponden…
Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation
Jiahao Lu, Jiacheng Deng
3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transform…