Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ROSEFusion: Random Optimization for Online Dense Reconstruction under Fast Camera Motion

About

Online reconstruction based on RGB-D sequences has thus far been restrained to relatively slow camera motions (<1m/s). Under very fast camera motion (e.g., 3m/s), the reconstruction can easily crumble even for the state-of-the-art methods. Fast motion brings two challenges to depth fusion: 1) the high nonlinearity of camera pose optimization due to large inter-frame rotations and 2) the lack of reliably trackable features due to motion blur. We propose to tackle the difficulties of fast-motion camera tracking in the absence of inertial measurements using random optimization, in particular, the Particle Filter Optimization (PFO). To surmount the computation-intensive particle sampling and update in standard PFO, we propose to accelerate the randomized search via updating a particle swarm template (PST). PST is a set of particles pre-sampled uniformly within the unit sphere in the 6D space of camera pose. Through moving and rescaling the pre-sampled PST guided by swarm intelligence, our method is able to drive tens of thousands of particles to locate and cover a good local optimum extremely fast and robustly. The particles, representing candidate poses, are evaluated with a fitness function defined based on depth-model conformance. Therefore, our method, being depth-only and correspondence-free, mitigates the motion blur impediment as ToF-based depths are often resilient to motion blur. Thanks to the efficient template-based particle set evolution and the effective fitness function, our method attains good quality pose tracking under fast camera motion (up to 4m/s) in a realtime framerate without including loop closure or global pose optimization. Through extensive evaluations on public datasets of RGB-D sequences, especially on a newly proposed benchmark of fast camera motion, we demonstrate the significant advantage of our method over the state of the arts.

Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu• 2021

Related benchmarks

TaskDatasetResultRank
Camera TrackingTUM RGB-D
Tracking Error (fr1/desk)2.3
23
Camera TrackingFastCaMo-Synth raw
ATE RMSE (Apartment 2)0.6
7
Camera TrackingFastCaMo-Synth noise (test)
ATE (Apart. 2)0.9
7
Camera TrackingETH3D camera shaking scenes
ATE-RMSE (camera_shake_1)0.9
7
3D ReconstructionFastCaMo-Real Apart. 2
Completeness84.4
4
3D ReconstructionFastCaMo-Real Lab
Completeness84.3
4
3D ReconstructionFastCaMo-Real Apart. 1
Completeness84.4
4
3D ReconstructionFastCaMo Real 20% frame drop
Completeness (Lou. 1)76.8
2
3D ReconstructionFastCaMo-Real Gym
Completeness43
2
3D ReconstructionFastCaMo-Real Avg.
Completeness74
2
Showing 10 of 11 rows

Other info

Follow for update