Download the BOiS - Berlin Object in Scene Database

The whole database can be downloaded as a single archive bois_db.zip (~24 GB) . Alternatively, all files belonging to the particular target object IDs can be downloaded as separate archives (TO_ID.zip) by clicking on the corresponding ID in the table below. All Meta information for the database is provided in a separate Excel file BOiSmeta.xls.

The archive containing the whole database, as well as the archives for individual target object IDs unpack into the same directory structure. The first folder “original_scenes_DxO” contains the distortion corrected scene images as PNG files with a resolution of 4272x2848 pixels. The scenes without target object are named O_<id>L_DxO.png, the scenes with the target object at the expected location O_<id>E_DxO.png, and the scene with the target object at the unexpected location O_<id>U_DxO.png.

The second folder “target_objects” contains a subfolder DxO, in which for each target object <id> one can find a folder TO_<id>_DxO with the corrected PNG images of the different views of the target objects, TO_<id>_<vertical angle>_<horizontal viewpoint>_DxO.png. These were down-sampled to 1152x786 pixel resolution in order to keep the total size of the database practicable. The third folder “masks” contains the segmentation masks of the scenes with the target object in expected (O_<id>E_m.png) and unexpected (O_<id>U_m.png) location at 4272x2848 pixel resolution.

The last folder “cpms” contains the contextual prior maps as gray level images (CPM_<id>.png) at 4272x2848 pixels resolution. Note that these maps are scaled to use the whole gray value range for visualization purposes and need to be normalized such that the sum over all pixels is 1 to ensure comparability across scenes.

In addition to the averaged and normalized contextual prior maps, we provide the 130 individual contextual prior segmentations of our 10 subjects at 600x400 pixels resolution (Indiviudal_priors_zip). These files are named <subject_id>_O_<id>L_s.png, where <subject_id> ranges from 2 to 11, and the gray values (0, 85, 170, 255) in the images encode the four prior probability levels from lowest to highest.

Indoor

ID Target Object ID Target Object ID Target Object
kitchen hall bathroom
6 pepper mill 25 bottle 1 bracelet
10 bread knife 61 shoes 8 body lotion
12 dishwashing brush 103 hand brush 19 shampoo
15 curry powder 112 lace 22 rubber duck
16 thermos flask top 113 scarf 31 hand soap
17 pot lid 121 flyer 40 toilet paper
20 egg 127 fire extinguishers 62 shampoo
26 bottle brush livingroom 79 urinal deodorizer block
29 fridge magnet 9 glasses 81 tooth brush
32 wooden spoon 13 CD 83 tooth paste
33 cactus 21 bottle of eggnogg 123 bowl with hair accessories
43 clock 23 remote control 124 sink plug
46 knife 27 yarn bedroom
47 milk 30 fireplace hook 11 clothes hanger
51 coffee filter 34 candle 18 Duden dictionary
55 scissors 36 cushion 41 pillow
58 dishwasher tab 44 battery charger 42 tie
59 dish sponge 50 music book 49 tie pin
60 mustard 65 toy 52 baby wipes
68 dishwashing detergent 76 cake server 80 alarm clock
69 sweetener 90 door handle 99 tablets
70 cup 100 tissue 104 belt
71 tea bag 102 vacuum cleaner nozzle other
74 toaster 126 flower 2 car key
75 pot office 38 infusion bag
77 straw 5 flip chart marker 48 cat food
78 kettle 7 pencil sharpener 53 pastry
88 painting 14 computer mouse 72 skull
92 iron 28 light bulb 82 pullingup aid
95 bottle lid 39 glue stick 101 door sign
110 banana 45 hole puncher 105 rubber glove
111 toast 54 scissors 106 paper towel
63 pen 109 disinfectant
67 watering can 116 screw-wrench
96 telephone receiver 117 cordless screwdriver bit
97 coffee mug cover 118 electrical plug
98 coin 119 adhesive bandage
107 cabinet key 129 sugar sprinkler
108 usb stick 130 banknote
122 adhesive tape

Outdoor

ID Target Object ID Target Object
garden park
4 broom brush 3 banana peel
35 shovel 56 bike lock
37 clothespin 66 toy digger
57 keys 73 table tennis bat
64 sock terrace
84 newspaper 24 lighter
86 garden watering can 85 folding rule
87 hose connection 91 coffee pot lid
89 swings other
93 Mercedes star 120 car wheel
94 pot plant 128 road sign
114 ashtray
115 cooking grate
125 thermometer