CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 date: Sun, 28 Dec 2025 21:21:26 GMT content-type: text/html; charset=utf-8 server: cloudflare last-modified: Sat, 22 Mar 2025 16:01:22 GMT access-control-allow-origin: * expires: Sun, 28 Dec 2025 21:31:26 GMT cache-control: max-age=600 report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=Gumyh5SbHVyWhCw5Al2PCCMuaAOpUOQMe0n9hGnFbKWImyN6916bVrpwDYLezOFYcMa6cTlmNNGUU9RTiS7b7%2Bl4AOUXLqeFO0WfMMne"}]} x-proxy-cache: MISS x-github-request-id: 54D3:3655F2:80A3FA:904B4E:69519F56 nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800} age: 0 via: 1.1 varnish x-served-by: cache-bom-vanm7210097-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766956887.756185,VS0,VE206 vary: Accept-Encoding x-fastly-request-id: ed372130325b7a5c048a8d1950c84fff5f317030 cf-cache-status: DYNAMIC content-encoding: gzip cf-ray: 9b541b7dfe8a4061-BOM alt-svc: h3=":443"; ma=86400 LabelMaker 🎨

ARKit LabelMaker 🏠

A New Scale for Indoor 3D Scene Understanding

CVPR 2025

Guangda Ji¹ Silvan Weder¹ Francis Engelmann^{1, 2, 3} Marc Pollefeys^{1, 4} Hermann Blum^{1, 5}

¹ETH Zürich ²Stanford ³Google ⁴Microsoft ⁵Uni Bonn / Lamarr Institute

Paper arXiv Code Dataset ScanNet SOTA

We complement ARKitScenes dataset with dense semantic annotations that are automatically generated at scale. This produces the first large-scale, real-world 3D dataset with dense semantic annotations. Training on this auto-generated data, we push forward the state-of-the-art performance on ScanNet and ScanNet200 with prevalent 3D semantic segmentation models.

Our dataset and model are powered by:

LabelMaker 🎨

Automatic Semantic Label Generation from RGB-D Trajectories

3DV 2024

Silvan Weder^{*, 1} Hermann Blum^{*, 1} Francis Engelmann^{1, 2, 3} Marc Pollefeys^{1, 4}

¹ETH Zürich ²ETH AI Center ³Google ⁴Microsoft

Paper arXiv Code

LabelMaker bundles a collection of state-of-the-art segmentation models with different sets of predicted classes in a neural field. LabelMaker can refine existing annotations and produce highly accurate 2D as well as 3D labels on ScanNet. At the same time, it opens new possibilities to rapidly label large-scale datasets without human effort.

Video

Qualitative results on ARKitScenes

LabelMaker can automatically create highly accurate 2D and 3D semantic segmentations. Below we show 3D semantic segmentation on ARKitScenes reconstructions.

Ashcan Backpack Bag Bannister Basket Bathtub Beanbag Bench Blanket Book Bookshelf Bottle Box Bucket Cabinet Ceiling Chair Chest of drawers Clock Column Curtain Cushion Decoration Display Door Doorframe Floor Footstool Furniture Lamp Laptop Light Microwave Oven Paper Paper cutter Picture Plant Printer Radiator Sack Stairway Table Teddy Tray Wall Window

Apparel Ashcan Bannister Basket Bed Blanket Book Bookshelf Bottle Bowl Box Cabinet Ceiling Chair Chest of drawers Clock Coffee table Curtain Cushion Desk Display Door Doorframe Floor Gat Lamp Light Mat Mirror Picture Radiator Shoe Shower stall Soap dispenser Stand Stool Swivel chair Table Teddy Telephone Towel Vent Wall Window

Ashcan Backpack Bed Blanket Book Bookshelf Bottle Box Cabinet Ceiling Chair Chest of drawers Clock Computer Computer keyboard Countertop Crate Curtain Cushion Decoration Desk Display Door Doorframe Fan Floor Footstool Kettle Lamp Mat Picture Plant Printer Radiator Swivel chair Table Teddy Telephone Towel Tray Wall Wardrobe Window

BibTeX


@inproceedings{Weder2024labelmaker,

  title = {{LabelMaker: Automatic Semantic Label Generation from RGB-D Trajectories}},

  author={Weder, Silvan and Blum, Hermann and Engelmann, Francis and Pollefeys, Marc},

  booktitle = {International Conference on 3D Vision (3DV)},

  year = {2024}
}


@inproceedings{Ji2024arkitlabelmaker,

  title = {{ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding}},

  author={Ji, Guangda and Weder, Silvan and Engelmann, Francis and Pollefeys, Marc and Blum, Hermann},

  year = {2024}
}

Original Source | Taken Source

ARKit LabelMaker 🏠 A New Scale for Indoor 3D Scene Understanding