# Towards 3D Object-Centric Feature Learning for Semantic Scene Completion

arXiv: https://arxiv.org/abs/2511.13031 · HTML: https://mlsanity.com/paper/2511.13031/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [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)
- [Attend, Infer, Repeat: Fast Scene Understanding with Generative Models](https://mlsanity.com/paper/1603.08575/) (2016)
- [GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2405.17429/) (2024)
- [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)
- [MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching](https://mlsanity.com/paper/2108.09770/) (2021)
- [Context and Geometry Aware Voxel Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2405.13675/) (2024)
- [OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries](https://mlsanity.com/paper/2312.03774/) (2023)
- [MonoOcc: Digging into Monocular Semantic Occupancy Prediction](https://mlsanity.com/paper/2403.08766/) (2024)
- [Adaptive Slot Attention: Object Discovery with Dynamic Slot Number](https://mlsanity.com/paper/2406.09196/) (2024)
- [Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion](https://mlsanity.com/paper/2407.02077/) (2024)
- [Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting](https://mlsanity.com/paper/2504.01957/) (2025)
- [ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention](https://mlsanity.com/paper/2401.00912/) (2024)
- [LOMA: Language-assisted Semantic Occupancy Network via Triplane Mamba](https://mlsanity.com/paper/2412.08388/) (2024)

## Abstract (arXiv)

Vision-based 3D Semantic Scene Completion (SSC) has received growing attention due to its potential in autonomous driving. While most existing approaches follow an ego-centric paradigm by aggregating and diffusing features over the entire scene, they often overlook fine-grained object-level details, leading to semantic and geometric ambiguities, especially in complex environments. To address this limitation, we propose Ocean, an object-centric prediction framework that decomposes the scene into individual object instances to enable more accurate semantic occupancy prediction. Specifically, we first employ a lightweight segmentation model, MobileSAM, to extract instance masks from the input image. Then, we introduce a 3D Semantic Group Attention module that leverages linear attention to aggregate object-centric features in 3D space. To handle segmentation errors and missing instances, we further design a Global Similarity-Guided Attention module that leverages segmentation features for global interaction. Finally, we propose an Instance-aware Local Diffusion module that improves instance features through a generative process and subsequently refines the scene representation in the BEV space. Extensive experiments on the SemanticKITTI and SSCBench-KITTI360 benchmarks demonstrate that Ocean achieves state-of-the-art performance, with mIoU scores of 17.40 and 20.28, respectively.