paper-with-me

Papers

Unsupervised Learning of Dense Optical Flow, Depth and Egomotion from Sparse Event Data

2018-09-23 · Chengxi Ye, Anton Mitrokhin, Cornelia Fermüller, James A. Yorke, Yiannis Aloimonos

In this work we present a lightweight, unsupervised learning pipeline for \textit{dense} depth, optical flow and egomotion estimation from sparse event output of the Dynamic Vision Sensor (DVS). To tackle this low level vision task, we use a novel encoder-decoder neural network architecture - ECN. Our work is the first monocular pipeline that generates dense depth and optical flow from sparse event data only. The network works in self-supervised mode and has just 150k parameters. We evaluate our pipeline on the MVSEC self driving dataset and present results for depth, optical flow and and egomotion estimation. Due to the lightweight design, the inference part of the network runs at 250 FPS on a single GPU, making the pipeline ready for realtime robotics applications. Our experiments demonstrate significant improvements upon previous works that used deep learning on event data, as well as the ability of our pipeline to perform well during both day and night.

📄 PDF Abstract BibTeX arXiv:1809.08625

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderGPUOptical Flow Estimation

Similar Papers 제목 키워드 기반

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization

2025-10-14 · Wenpu Li, Bangyan Liao, Yi Zhou, Qi Xu 외 arxiv

The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras), however, the lack of robust data associa…

Optical Flow EstimationDepth Estimation

Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion

2018-12-19 · CVPR 2019 6 · Alex Zihao Zhu, Liangzhe Yuan, Kenneth Chaney, Kostas Daniilidis

In this work, we propose a novel framework for unsupervised learning for event cameras that learns motion information from only the event stream. In particular, we propose an input representation of the events in the for…

Optical Flow Estimation

Unsupervised Learning of Depth, Camera Pose and Optical Flow from Monocular Video

2022-05-19 · Dipan Mandal, Abhilash Jain

We propose DFPNet -- an unsupervised, joint learning system for monocular Depth, Optical Flow and egomotion (Camera Pose) estimation from monocular image sequences. Due to the nature of 3D scene geometry these three comp…

Camera Pose EstimationImage ReconstructionOptical Flow EstimationPose Estimation

Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization

2020-02-26 · Shihao Jiang, Dylan Campbell, Miaomiao Liu, Stephen Gould 외

We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brig…

Motion EstimationOptical Flow Estimation

Motion Segmentation and Egomotion Estimation from Event-Based Normal Flow

2025-07-19 · Zhiyuan Hua, Dehao Yuan, Cornelia Fermüller arxiv

This paper introduces a robust framework for motion segmentation and egomotion estimation using event-based normal flow, tailored specifically for neuromorphic vision sensors. In contrast to traditional methods that rely…

Motion SegmentationDepth Estimation