Two-Stage Adaptive Object Scene Flow Using Hybrid CNN-CRF Model

Li, Congcong; Ma, Haoyu; Liao, Qingmin

doi:10.1109/icpr48806.2021.9413289

Cited by 15 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we compare to the more recent learned approaches ACOSF [12] and RigidMask [30]. ACOSF takes a similar approach as OSF but employs deep networks to estimate optical flow and disparity.…”

Section: Object-rigid Modelsmentioning

confidence: 99%

See 1 more Smart Citation

SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection

Sommer¹,

Philipp²,

Brox³

2022

Preprint

View full text Add to dashboard Cite

We propose SF2SE3, a novel approach to estimate scene dynamics in form of a segmentation into independently moving rigid objects and their SE(3)-motions. SF2SE3 operates on two consecutive stereo or RGB-D images. First, noisy scene flow is obtained by application of existing optical flow and depth estimation algorithms. SF2SE3 then iteratively (1) samples pixel sets to compute SE(3)-motion proposals, and (2) selects the best SE(3)-motion proposal with respect to a maximum coverage formulation. Finally, objects are formed by assigning pixels uniquely to the selected SE(3)-motions based on consistency with the input scene flow and spatial proximity. The main novelties are a more informed strategy for the sampling of motion proposals and a maximum coverage formulation for the proposal selection. We conduct evaluations on multiple datasets regarding application of SF2SE3 for scene flow estimation, object segmentation and visual odometry. SF2SE3 performs on par with the state of the art for scene flow estimation and is more accurate for segmentation and odometry.

show abstract

Section: Object-rigid Modelsmentioning

confidence: 99%

“…Regarding related work, SF2SE3 is most similar to ACOSF [12] in that it approaches the problem as iteratively finding SE(3)-motion proposals and optimizing an assignment of pixels to the proposals. However, SF2SE3 introduces several improvements.…”

Section: Introductionmentioning

confidence: 99%