paper-with-me

Papers

Rendering and Tracking the Directional TSDF: Modeling Surface Orientation for Coherent Maps

2021-08-18 · Malte Splietker, Sven Behnke

Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation or grasping. The recently presented Directional Truncated Signed Distance Function (DTSDF) is an augmentation of the regular TSDF and shows potential for more coherent maps and improved tracking performance. In this work, we present methods for rendering depth- and color maps from the DTSDF, making it a true drop-in replacement for the regular TSDF in established trackers. We evaluate and show, that our method increases re-usability of mapped scenes. Furthermore, we add color integration which notably improves color-correctness at adjacent surfaces.

📄 PDF Abstract BibTeX arXiv:2108.08115

Code (1)

AIS-Bonn/DirectionalTSDF

Similar Papers 제목 키워드 기반

Rendering the Directional TSDF for Tracking and Multi-Sensor Registration with Point-To-Plane Scale ICP

2023-01-30 · Malte Splietker, Sven Behnke

Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation and manipulation. The recently presented Directional Truncated Signed Distance Function (DTSDF…

Directional TSDF: Modeling Surface Orientation for Coherent Meshes

2019-08-14 · Malte Splietker, Sven Behnke

Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping. The popular method of fusing depth information into a truncated signed distanc…

3D Reconstruction

TSDF-Sampling: Efficient Sampling for Neural Surface Field using Truncated Signed Distance Field

2023-11-29 · Chaerin Min, Sehyun Cha, Changhee Won, Jongwoo Lim

Multi-view neural surface reconstruction has exhibited impressive results. However, a notable limitation is the prohibitively slow inference time when compared to traditional techniques, primarily attributed to the dense…

Surface Reconstruction

ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces

2023-08-15 · ICCV 2023 1 · Qianyi Wu, Kaisiyuan Wang, Kejie Li, Jianmin Zheng 외

In recent years, neural implicit surface reconstruction has emerged as a popular paradigm for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods lever…

3D ReconstructionMulti-View 3D ReconstructionObjectObject Reconstruction+1

Human Performance Modeling and Rendering via Neural Animated Mesh

2022-09-18 · Fuqiang Zhao, Yuheng Jiang, Kaixin Yao, Jiakai Zhang 외

We have recently seen tremendous progress in the neural advances for photo-real human modeling and rendering. However, it's still challenging to integrate them into an existing mesh-based pipeline for downstream applicat…