Related papers: POSEFusion: Pose-guided Selective Fusion for Singl…

Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features…

In recent years, modern techniques in deep learning and large-scale datasets have led to impressive progress in 3D instance segmentation, grasp pose estimation, and robotics. This allows for accurate detection directly in 3D scenes, object-…

Infrared-visible image fusion aims to create an information-rich fused image by integrating the complementary thermal saliency from infrared sensing and fine textures from visible imaging. Such accurate fusion is essential for real-world…

Reconstructing 3D models from single-view images is a long-standing problem in computer vision. The latest advances for single-image 3D reconstruction extract a textual description from the input image and further utilize it to synthesize…

We present the first real-time system capable of tracking and reconstructing, individually, every visible object in a given scene, without any form of prior on the rigidness of the objects, texture existence, or object category. In contrast…

Monocular 3D human pose estimation poses significant challenges due to the inherent depth ambiguities that arise during the reprojection process from 2D to 3D. Conventional approaches that rely on estimating an over-fit projection matrix…

We propose a 6D RGB-D odometry approach that finds the relative camera pose between consecutive RGB-D frames by keypoint extraction and feature matching both on the RGB and depth image planes. Furthermore, we feed the estimated pose to the…

Accurately estimating 3D hand pose is crucial for understanding how humans interact with the world. Despite remarkable progress, existing methods often struggle to generate plausible hand poses when the hand is heavily occluded or blurred.…

In the realm of robotic grasping, achieving accurate and reliable interactions with the environment is a pivotal challenge. Traditional methods of grasp planning methods utilizing partial point clouds derived from depth image often suffer…

In extreme scenarios such as nighttime or low-visibility environments, achieving reliable perception is critical for applications like autonomous driving, robotics, and surveillance. Multi-modality image fusion, particularly integrating…

Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. Deep learning-based image fusion algorithms face significant challenges, including the lack of a…

We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information. Unlike existing methods that either use multi-stage pipelines or hold sensor and dataset-specific assumptions,…

Localized subject-driven image editing aims to seamlessly integrate user-specified objects into target scenes. As generative models continue to scale, training becomes increasingly costly in terms of memory and computation, highlighting the…

We propose an approach for 3D reconstruction and segmentation of a single object placed on a flat surface from an input video. Our approach is to perform dense depth map estimation for multiple views using a proposed objective function that…

We propose Geo-PIFu, a method to recover a 3D mesh from a monocular color image of a clothed person. Our method is based on a deep implicit function-based representation to learn latent voxel features using a structure-aware 3D U-Net, to…

Deep learning approaches for Visual-Inertial Odometry (VIO) have proven successful, but they rarely focus on incorporating robust fusion strategies for dealing with imperfect input sensory data. We propose a novel end-to-end selective…

Estimating the 2D human poses in each view is typically the first step in calibrated multi-view 3D pose estimation. But the performance of 2D pose detectors suffers from challenging situations such as occlusions and oblique viewing angles.…

6D object pose estimation is widely applied in robotic tasks such as grasping and manipulation. Prior methods using RGB-only images are vulnerable to heavy occlusion and poor illumination, so it is important to complement them with depth…

Accurate 3D reconstruction in visually-degraded underwater environments remains a formidable challenge. Single-modality approaches are insufficient: vision-based methods fail due to poor visibility and geometric constraints, while sonar is…

Efficient Visual-Inertial Odometry (VIO) is crucial for payload-constrained robots. Though modern optimization-based algorithms have achieved superior accuracy, the MSCKF-based VIO algorithms are still widely demanded for their efficient…