MICC-SRI Dataset Semantic Road Inpainting

MICC Semantic Road Inpainting (MICC-SRI) Dataset

The dataset contains 11,913 frame pairs of urban driving footage with and without moving objects, synthetically generated with the CARLA simulator. All frames are available both as RGB images and semantic segmentations. RGB images are non-photorealistic being rendered by a game engine, while semantic segmentations are similar to a real-world segmentations. The dataset is designed to provide a supervision for semantic road inpainting tasks.

Download Dataset

We collected a synthetically generated dataset using the CARLA simulator, a driving simulator based on the physics engine Unreal Engine.We run different simulations with CARLA, collecting both rendered RGB frames and synthetically generated semantic segmentations.

In order to acquire both scenes with and without dynamic objects, we first run the simulation inserting vehicles and pedestrians with an autopilot and we store all the driving commands generated by the autopilot. These commands are then used to run a second identical simulation without dynamic objects.

A different simulation is run for 1000 frames from each spawning point of both the available maps in CARLA.

Simulations are run at 3 FPS and subsampled to take an image every 3 seconds to ensure diversity. Occasional unalignments between the two versions of the data (e.g. due to car accidents) are removed in a post processing step.In total we have collected 11,913 frames.

Dynamic objects included in the current version of CARLA (v0.8.2) are Cars and Pedestrians. We plan to collect additional data when new object classes will become available in CARLA.

The full dataset can be downloaded at the following links::

Publications: if you use this dataset please cite our paper:

  title={Road layout understanding by generative adversarial inpainting},
  author={Berlincioni, Lorenzo and Becattini, Federico and Galteri, Leonardo and Seidenari, Lorenzo and Del Bimbo, Alberto},
  booktitle={Inpainting and Denoising Challenges},

There are no related projects