Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web

[IROS 23] InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data

[CVPR 2023 Highlight 💡] Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision

[RA-L 25] Self-Supervised Diffusion-Based Scene Flow Estimation and Motion Segmentation with 4D Radar

On solutions to the problem of Event Collapse in Motion Compensation frameworks

This repo contains Python scripts to apply a Dense CRF to refine outputs from a motion segmentation algorithm.

Robust motion detection/segmentation using OpenCV

Code for paper: Motion Segmentation for Neuromorphic Aerial Surveillance, arXiv 2024

[ECCV 2024] RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes

Proposed Self-Supervised Approach for Sparse to Dense Motion Segmentation

M.S. thesis — multi-body motion-segmentation architecture for arbitrary numbers of disordered 3D point sets (PyTorch, C++).

Website for our 3DV 2021 paper "Self-Supervised Monocular Scene Decomposition and Depth Estimation".

ML research to segment scene from moving ego vehicle into static and dynamic pixels