paper-with-me

Papers

Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes

2018-04-24 · André Apitzsch, Roman Seidel, Gangolf Hirtz

Optical flow estimation with convolutional neural networks (CNNs) has recently solved various tasks of computer vision successfully. In this paper we adapt a state-of-the-art approach for optical flow estimation to omnidirectional images. We investigate CNN architectures to determine high motion variations caused by the geometry of fish-eye images. Further we determine the qualitative influence of texture on the non-rigid object to the motion vectors. For evaluation of the results we create ground truth motion fields synthetically. The ground truth contains cubes with static background. We test variations of pre-trained FlowNet 2.0 architectures by indicating common error metrics. We generate competitive results for the motion of the foreground with inhomogeneous texture on the moving object.

📄 PDF Abstract BibTeX arXiv:1804.09004

Code (1)

https://gitlab.com/auxilia/cubes3d 공식 구현

Tasks

ObjectOptical Flow Estimation

Similar Papers 제목 키워드 기반

OmniFlow: Human Omnidirectional Optical Flow

2021-04-16 · Roman Seidel, André Apitzsch, Gangolf Hirtz

Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to …

Optical Flow Estimation

Learning Omnidirectional Flow in 360-degree Video via Siamese Representation

2022-08-07 · Keshav Bhandari, Bin Duan, Gaowen Liu, Hugo Latapie 외

Optical flow estimation in omnidirectional videos faces two significant issues: the lack of benchmark datasets and the challenge of adapting perspective video-based methods to accommodate the omnidirectional nature. This…

DiversityOptical Flow EstimationRepresentation Learning

Optical Flow Estimation in 360$^\circ$ Videos: Dataset, Model and Application

2023-01-27 · Bin Duan, Keshav Bhandari, Gaowen Liu, Yan Yan

Optical flow estimation has been a long-lasting and fundamental problem in the computer vision community. However, despite the advances of optical flow estimation in perspective videos, the 360$^\circ$ videos counterpart…

Activity RecognitionEgocentric Activity RecognitionOptical Flow EstimationRepresentation Learning

OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities

2024-12-21 · CVPR 2025 1 · Suyoung Lee, JaeYoung Chung, Kihoon Kim, Jaeyoo Huh 외

Feed-forward 3D Gaussian splatting (3DGS) models have gained significant popularity due to their ability to generate scenes immediately without needing per-scene optimization. Although omnidirectional images are becoming…

3DGSImage Stitching

360° Optical Flow using Tangent Images

2021-12-28 · Mingze Yuan, Christian Richardt

Omnidirectional 360{\deg} images have found many promising and exciting applications in computer vision, robotics and other fields, thanks to their increasing affordability, portability and their 360{\deg} field of view.…

ERPOptical Flow Estimation