Live Reconstruction of Large-Scale Dynamic Outdoor Worlds

03/15/2019
by   Ondrej Miksik, et al.
26

Standard 3D reconstruction pipelines assume stationary world, therefore suffer from "ghost artifacts" whenever dynamic objects are present in the scene. Recent approaches has started tackling this issue, however, they typically either only discard dynamic information, represent it using bounding boxes or per-frame depth or rely on approaches that are inherently slow and not suitable to online settings. We propose an end-to-end system for live reconstruction of large-scale outdoor dynamic environments. We leverage recent advances in computationally efficient data-driven approaches for 6 DoF object pose estimation to segment the scene into objects and stationary "background". This allows us to represent the scene using a time-dependent (dynamic) map, in which each object is explicitly represented as a separate instance and reconstructed in its own volume. For each time step, our dynamic map maintains a relative pose of each volume with respect to the stationary background. Our system operates in incremental manner which is essential for on-line reconstruction, handles large-scale environments with objects at large distances and runs in (near) real-time. We demonstrate the efficacy of our approach on the KITTI dataset, and provide qualitative and quantitative results showing high-quality dense 3D reconstructions of a number of dynamic scenes.

READ FULL TEXT

page 1

page 2

page 5

page 6

page 7

page 8

research
02/24/2017

Automatic segmentation of agricultural objects in dynamic outdoor environments

Segmentation in dynamic outdoor environments can be difficult when the i...
research
05/16/2021

TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction

The ability to simultaneously track and reconstruct multiple objects mov...
research
03/02/2023

Semantic Attention Flow Fields for Dynamic Scene Decomposition

We present SAFF: a dynamic neural volume reconstruction of a casual mono...
research
08/02/2021

PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time

Dynamic environments that include unstructured moving objects pose a har...
research
03/25/2023

SUDS: Scalable Urban Dynamic Scenes

We extend neural radiance fields (NeRFs) to dynamic large-scale urban sc...
research
01/25/2018

Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation

Reconstructing dense, volumetric models of real-world 3D scenes is impor...
research
12/13/2019

Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar

Conventional sensor systems record information about directly visible ob...

Please sign up or login with your details

Forgot password? Click here to reset