The dataset consists of frames from the Lethal Company video game, collected during 11 different play sessions (1). Each frame is accompanied with a mask that describes positions of all the scrap in the frame, and another mask for all the monsters. Frames were captured from two different indoor areas (factory and castle) and multiple outdoor areas (planets Assurance, Rend and others). Frames contain about 20 different loot items (keys, airhorns, big bolts and many more) and about 10 different monsters (coil-heads, nutcrackers, thompers and so on). Sometimes scrap and monsters are partially occluded by other in-game objects - then only the non-occluded portion(s) should be segmented. Due to how the game is programmed, some objects might intersect. Both images and masks are in 860x520 resolution (2).

Sometimes objects receive shadows or are positioned in a very dark or foggy area, which can make them very hard to detect. It is possible that a tiny minority of the objects are completely indetectable. Please note that the in-game brightness (“gamma”) setting may be slightly different for different frames. It is guaranteed that there are no images in the dataset that contain more than 0, but less than 20 pixels in their loot mask, and/or more than 0, but less than 40 pixels in their monster mask. 

The train split contains 15 000 frames. The train split was pre-balanced - out of all the loot masks, 6000 contain loot, and out of all the monster masks, 3 000 contain monster(s). Test split (hidden from you) consists of 13 988 frames. These frames were collected during different play sessions, than frames from the train split. They were not balanced, and thus about 8% of monster masks contain monsters, and about 30% of loot masks contain loot. The total volume of the dataset is approximately 8.6GB.

Screenshots with corresponding masks for enemies and loot:
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F7184772%2Fbfbf29be3c4d2cdd43cb757e3890deb6%2Fdownload.png?generation=1713020031933135&alt=media)


(1) The code for capturing the frames and deriving masks, as well as the code used for balancing the dataset, is publicly available in the GitHub: https://github.com/semjon00/LethalCompanySegmentation

(2) Due to an artistic choice of the game author, the game world is rendered in 860x520 resolution. Afterwards, this render is upscaled to the actual window/monitor dimensions, and some additional elements are added to the frame. Thus, in this dataset the images are provided in the game’s native resolution.