# Unleashing Semantic and Geometric Priors for 3D Scene Completion

arXiv: https://arxiv.org/abs/2508.13601 · HTML: https://mlsanity.com/paper/2508.13601/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving](https://mlsanity.com/paper/2311.16038/) (2023)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [Attentional Feature Fusion](https://mlsanity.com/paper/2009.14082/) (2020)
- [FB-BEV: BEV Representation from Forward-Backward View Transformations](https://mlsanity.com/paper/2308.02236/) (2023)
- [Symphonize 3D Semantic Scene Completion with Contextual Instance Queries](https://mlsanity.com/paper/2306.15670/) (2023)
- [SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving](https://mlsanity.com/paper/2306.09001/) (2023)
- [Improving 2D Feature Representations by 3D-Aware Fine-Tuning](https://mlsanity.com/paper/2407.20229/) (2024)
- [Context and Geometry Aware Voxel Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2405.13675/) (2024)
- [EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding](https://mlsanity.com/paper/2412.04380/) (2024)
- [Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion](https://mlsanity.com/paper/2407.02077/) (2024)
- [DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation](https://mlsanity.com/paper/2504.04701/) (2025)
- [Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion](https://mlsanity.com/paper/2303.13959/) (2023)
- [LOMA: Language-assisted Semantic Occupancy Network via Triplane Mamba](https://mlsanity.com/paper/2412.08388/) (2024)
- [VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion](https://mlsanity.com/paper/2503.06219/) (2025)

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

- [Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI](https://mlsanity.com/paper/2606.22971/) (2026)
- [VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion](https://mlsanity.com/paper/2512.18954/) (2025)

## Abstract (arXiv)

Camera-based 3D semantic scene completion (SSC) provides dense geometric and semantic perception for autonomous driving and robotic navigation. However, existing methods rely on a coupled encoder to deliver both semantic and geometric priors, which forces the model to make a trade-off between conflicting demands and limits its overall performance. To tackle these challenges, we propose FoundationSSC, a novel framework that performs dual decoupling at both the source and pathway levels. At the source level, we introduce a foundation encoder that provides rich semantic feature priors for the semantic branch and high-fidelity stereo cost volumes for the geometric branch. At the pathway level, these priors are refined through specialised, decoupled pathways, yielding superior semantic context and depth distributions. Our dual-decoupling design produces disentangled and refined inputs, which are then utilised by a hybrid view transformation to generate complementary 3D features. Additionally, we introduce a novel Axis-Aware Fusion (AAF) module that addresses the often-overlooked challenge of fusing these features by anisotropically merging them into a unified representation. Extensive experiments demonstrate the advantages of FoundationSSC, achieving simultaneous improvements in both semantic and geometric metrics, surpassing prior bests by +0.23 mIoU and +2.03 IoU on SemanticKITTI. Additionally, we achieve state-of-the-art performance on SSCBench-KITTI-360, with 21.78 mIoU and 48.61 IoU.