Related references
Note: Only part of the references are listed.
Article
Computer Science, Theory & Methods
Zhenbiao Gai et al.
IMAGE AND VISION COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yi Wei et al.
Summary: In this work, a new multi-view depth estimation method called NerfingMVS is presented, which combines conventional reconstruction and learning-based priors with neural radiance fields (NeRF). It directly optimizes over implicit volumes, eliminating the need for pixel matching in indoor scenes. The key is using learning-based priors to guide the optimization process of NeRF. The proposed method achieves state-of-the-art performances and improves rendering quality on both seen and novel views.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Robotics
Xuan Yu et al.
Summary: This letter proposes a method called NF-Atlas, which combines neural feature volumes with pose graph optimization and achieves both local rigidity and global elasticity. The neural feature volume employs a sparse feature Octree and a small MLP to encode the submap's signed distance function, allowing for end-to-end solving of probabilistic mapping. The map is built incrementally volume by volume, avoiding catastrophic forgetting, and updating only the origin of neural volumes is required in case of a loop closure.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Qian Yu et al.
Summary: This paper proposes a Part-Wise AtlasNet method based on the architecture of AtlasNet, which imposes constraints on the local structures of 3D objects by restricting each neural network to reconstructing a specific part of the object. The experimental results demonstrate that the proposed method generates structured point clouds with higher visual quality and better performance in 3D point cloud generation from a single image compared to other methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Chemistry, Analytical
Ignacio Vizzo et al.
Summary: This paper presents a practical approach to volumetric surface reconstruction based on truncated signed distance functions (TSDFs), which is suitable for systems with different environments and sensors. By utilizing the OpenVDB library, an effective 3D map representation is achieved, and a C++ and Python library is provided to solve volumetric mapping problems with TSDFs.
Article
Robotics
Michal Adamkiewicz et al.
Summary: The article introduces the use of NeRF for representing 3D scenes, and proposes an algorithm for robot navigation using an RGB camera, including trajectory optimization and pose estimation methods. By combining the trajectory planner with the pose filter in an online replanning loop, a vision-based robot navigation pipeline is established.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
David Hoeller et al.
Summary: We propose a learning-based method for reconstructing local terrain for mobile robots in urban environments. The algorithm utilizes depth measurements and the robot's trajectory to estimate the topography in the robot's vicinity. The method is able to accurately reconstruct the terrain despite noisy measurements and missing data.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Jianglong Ye et al.
Summary: This paper proposes a novel framework that utilizes video data to simultaneously track and reconstruct 3D objects using a neural implicit function. By iteratively improving the shape reconstruction and tracking performance, significant improvements are shown on two datasets.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Software Engineering
William E. Lorensen
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2020)
Article
Chemistry, Analytical
Yan Yan et al.
Article
Computer Science, Artificial Intelligence
Jose-Raul Ruiz-Sarmiento et al.
KNOWLEDGE-BASED SYSTEMS
(2017)
Article
Computer Science, Artificial Intelligence
Armin Hornung et al.
Article
Geography, Physical
Shi Pu et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2009)