# Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perception

arXiv: https://arxiv.org/abs/2509.26087 · HTML: https://mlsanity.com/paper/2509.26087/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 81 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 30 of 61)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)
- [A Simple Framework for Open-Vocabulary Segmentation and Detection](https://mlsanity.com/paper/2303.08131/) (2023)
- [GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2405.17429/) (2024)
- [SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction](https://mlsanity.com/paper/2311.12754/) (2023)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?](https://mlsanity.com/paper/2206.07959/) (2022)
- [RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision](https://mlsanity.com/paper/2309.09502/) (2023)

## Built on by (most cited first, 2 of 2)

- [ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation](https://mlsanity.com/paper/2511.15396/) (2025)
- [FreeOcc: Training-free Panoptic Occupancy Prediction via Foundation Models](https://mlsanity.com/paper/2603.06166/) (2026)

## Abstract (arXiv)

In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable road users such as pedestrians and cyclists. Previous representation methods, such as Bird's Eye View, collapse vertical information, leading to ambiguity in 3D object localisation and limiting accurate understanding of the environment for downstream tasks such as motion planning and scene forecasting. In contrast, semantic occupancy provides a full 3D representation of the surroundings, addressing these limitations. Unlike supervised methods that rely on manually annotated data, self-supervised approaches use 2D pseudo-labels, improving scalability by reducing the need for labour-intensive annotation. Consequently, such models employ techniques such as novel view synthesis, cross-view rendering, and depth estimation to allow for model supervision against the 2D labels. However, such approaches often incur high computational and memory costs during training, especially for novel view synthesis. To address these issues, we propose Easy3D-Labels, which are 3D pseudo-ground-truth labels generated using Grounded-SAM and Metric3Dv2, with temporal aggregation for densification, permitting supervision directly in 3D space. Easy3D-Labels can be readily integrated into existing models to provide model supervision, yielding substantial performance gains, with mIoU increasing by 45% and RayIoU by 49% when applied to OccNeRF on the Occ3D-nuScenes dataset. Additionally, we introduce EasyOcc, a streamlined model trained solely on these 3D pseudo-labels, avoiding the need for complex rendering strategies and achieving 15.7 mIoU on Occ3D-nuScenes. Easy3D-Labels improve scene understanding by reducing object duplication and enhancing depth estimation accuracy, as reflected by improvements in the RayIoU metric.