dimagrshk/opt_flow_attack

Attacking Optical Flow

This project is based on the Attacking Optical Flow. Authors shows that adversarial attacks can corrupt optical flow estimation and tests different architectures. In general latest approaches have more stable behavior.
Code is based on mmflow framework.

Purpose of this work

[x] Collect models for optical flow estimation and make it runnable to test
[x] Reproduce adversarial attack as it shown in the paper
[] Attempt to optimize specific adversarial patch for selected models

Selected models

• Flownet
• PWCnet
• RAFT

Dataset

Sintel dataset were selected for testing and reproducing.

Experiments

For each model were 3 runs without any patches, with white patch, with universal patch.

• White patch
• Universal patch

Metric

EPE was used to measure impact of adding patches.

Metric Results

Model	Baseline	White Patch	Adversarial patch
FlowNet	4.5552	6.3561	6.578
PWCnet	2.012	4.308	4.437
RAFT	1.471	3.731	3.844

Visual Results

Link to gdrive with .mp4

TODO

[] Test on more datasets
[] Attempt to optimize specific patch