Contextual Building Massing Generation (CoMa)

Role: R&D Leader, Sber AI

Period: Feb 2026 – present

Massing — the first rough 3D volume of a future building — has to fit the site, its urban context and the economic and programmatic constraints of the project. We frame massing generation as a conditional task for vision-language models that produce site-aware 3D volumes.

We introduced CoMa-20K, a dataset that pairs detailed massing geometries with economic and programmatic data and imagery of the development site in its urban context, benchmarked fine-tuned and large zero-shot vision-language models, and proposed a learned contextual relevance metric (Maslov et al., 2026). The dataset, model weights and code are publicly available.

The project is part of our broader work on generative AI for architecture at Sber AI, which also includes floor plan generation and interior layout synthesis.

References

2026

Smart Cities
CoMa: Contextual Massing Generation with Vision-Language Models

Evgenii Maslov, Aleksandra Vabnits, Vladimir Vorona, Anastasia Antsiferova, Valentin Khrulkov, Anastasia Volkova, Anton Gusarov, Andrey Kuznetsov, and Ivan Oseledets

Smart Cities, 2026

Abs DOI arXiv Bib HTML Code

We frame building massing generation as a conditional task for vision-language models that must produce site-aware 3D volumes. We introduce CoMa-20K, a dataset that pairs detailed massing geometries with economic and programmatic data and visual representations of the development site within its urban context, benchmark fine-tuned and large zero-shot vision-language models, and propose a learned contextual relevance metric.
@article{maslovComa2026, title = {{CoMa: Contextual Massing Generation with Vision-Language Models}}, author = {Maslov, Evgenii and Vabnits, Aleksandra and Vorona, Vladimir and Antsiferova, Anastasia and Khrulkov, Valentin and Volkova, Anastasia and Gusarov, Anton and Kuznetsov, Andrey and Oseledets, Ivan}, year = {2026}, journal = {Smart Cities}, volume = {9}, number = {9}, pages = {153}, doi = {10.3390/smartcities9090153}, }