Search
Results
-
Shape As Points: A Differentiable Poisson Solver
(2021)Advances in Neural Information Processing Systems 34In recent years, neural implicit representations gained popularity in 3D reconstruction due to their expressiveness and flexibility. However, the implicit nature of neural implicit representations results in slow inference times and requires careful initialization. In this paper, we revisit the classic yet ubiquitous point cloud representation and introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson ...Conference Paper -
LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies
(2021)2021 International Conference on 3D Vision (3DV)3D representation and reconstruction of human bodies have been studied for a long time in computer vision. Traditional methods rely mostly on parametric statistical linear models, limiting the space of possible bodies to linear combinations. It is only recently that some approaches try to leverage neural implicit representations for human body modeling, and while demonstrating impressive results, they are either limited by representation ...Conference Paper -
NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis
(2021)2021 International Conference on 3D Vision (3DV)Building upon the recent progress in novel view synthesis, we propose its application to improve monocular depth estimation. In particular, we propose a novel training method split in three main steps. First, the prediction results of a monocular depth network are warped to an additional view point. Second, we apply an additional image synthesis network, which corrects and improves the quality of the warped RGB image. The output of this ...Conference Paper -
Privacy Preserving Localization and Mapping from Uncalibrated Cameras
(2021)2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Recent works on localization and mapping from privacy preserving line features have made significant progress towards addressing the privacy concerns arising from cloud-based solutions in mixed reality and robotics. The requirement for calibrated cameras is a fundamental limitation for these approaches, which prevents their application in many crowd-sourced mapping scenarios. In this paper, we propose a solution to the uncalibrated privacy ...Conference Paper -
Holistic 3D Scene Understanding From a Single Image With Implicit Representation
(2021)2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)We present a new pipeline for holistic 3D scene understanding from a single image, which could predict object shapes, object poses, and scene layout. As it is a highly ill-posed problem, existing methods usually suffer from inaccurate estimation of both shapes and layout especially for the cluttered scene due to the heavy occlusion between objects. We propose to utilize the latest deep implicit representation to solve this challenge. We ...Conference Paper -
LIC-Fusion 2.0: LiDAR-Inertial-Camera Odometry with Sliding-Window Plane-Feature Tracking
(2020)2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Multi-sensor fusion of multi-modal measurements from commodity inertial, visual and LiDAR sensors to provide robust and accurate 6DOF pose estimation holds great potential in robotics and beyond. In this paper, building upon our prior work (i.e., LIC-Fusion), we develop a sliding-window filter based LiDAR-Inertial-Camera odometry with online spatiotemporal calibration (i.e., LIC-Fusion 2.0), which introduces a novel sliding-window ...Conference Paper -
NeuralMeshing: Differentiable Meshing of Implicit Neural Representations
(2022)Lecture Notes in Computer Science ~ Pattern RecognitionThe generation of triangle meshes from point clouds, i.e. meshing, is a core task in computer graphics and computer vision. Traditional techniques directly construct a surface mesh using local decision heuristics, while some recent methods based on neural implicit representations try to leverage data-driven approaches for this meshing process. However, it is challenging to define a learnable representation for triangle meshes of unknown ...Conference Paper -
Camera Pose Estimation using Implicit Distortion Models
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Low-dimensional parametric models are the de-facto standard in computer vision for intrinsic camera calibration. These models explicitly describe the mapping between incoming viewing rays and image pixels. In this paper, we explore an alternative approach which implicitly models the lens distortion. The main idea is to replace the parametric model with a regularization term that ensures the latent distortion map varies smoothly throughout ...Conference Paper -
Context-Aware Sequence Alignment using 4D Skeletal Augmentation
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality. State-of-the-art methods directly learn image-based embedding space by leveraging powerful deep convolutional neural networks. While being straightforward, their results are far from satisfactory, the aligned videos exhibit severe temporal discontinuity without additional post-processing steps. ...Conference Paper -
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over-smoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. ...Conference Paper