---
title: "Visual Implicit Geometry Transformer for Autonomous Driving"
authors:
  - "Arsenii Shirokov"
  - "Mikhail Kuznetsov"
  - "Danila Stepochkin"
  - "Egor Evdokimov"
  - "Daniil Glazkov"
  - "Nikolay Patakin"
  - "Anton Konushin"
  - "Dmitry Senushkin"
doi: "10.24963/ijcai.2026/179"
url: "https://ijcai.org/proceedings/2026/179"
pdf: "https://ijcai.org/proceedings/2026/0179.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1604-1612"
track: "Main Track"
keywords:
  - "Computer Vision: 3D computer vision"
  - "Computer Vision: Scene analysis and understanding"
---

# Visual Implicit Geometry Transformer for Autonomous Driving

Arsenii Shirokov, Mikhail Kuznetsov, Danila Stepochkin, Egor Evdokimov, Daniil Glazkov, Nikolay Patakin, Anton Konushin, Dmitry Senushkin

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1604-1612. DOI: [10.24963/ijcai.2026/179](https://doi.org/10.24963/ijcai.2026/179)

## Abstract

We introduce the Visual Implicit Geometry Transformer (ViGT), an autonomous driving geometric model that estimates continuous 3D occupancy fields from surround-view camera rigs. ViGT represents a step towards foundational geometric models for autonomous driving, prioritizing scalability, architectural simplicity, and generalization across diverse sensor configurations. Our approach achieves this through a calibration-free architecture, enabling a single model to adapt to different sensor setups. 
    Unlike general-purpose geometric foundational models that focus on pixel-aligned predictions, ViGT estimates a continuous 3D occupancy field in a bird’s-eye-view (BEV) addressing domain-specific requirements.
    ViGT naturally infers geometry from multiple camera views into a single metric coordinate frame, providing a common representation for multiple geometric tasks.
    Unlike most existing occupancy models, we adopt a self-supervised training procedure that leverages synchronized image-LiDAR pairs, eliminating the need for costly manual annotations.
    We validate the scalability and generalizability of our approach by training our model on a mixture of five large-scale autonomous driving datasets (NuScenes, Waymo, NuPlan, ONCE, and Argoverse) and achieving state-of-the-art performance on the pointmap estimation task, with the best average rank across all evaluated baselines. 
    We further evaluate ViGT on the Occ3D-nuScenes benchmark, where ViGT achieves comparable performance with supervised methods.