# Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction

arXiv: https://arxiv.org/abs/2412.08243 · HTML: https://mlsanity.com/paper/2412.08243/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 83 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 30 of 55)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [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)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [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)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (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)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception](https://mlsanity.com/paper/2303.03991/) (2023)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)

## Built on by (most cited first, 8 of 8)

- [OmniNWM: Omniscient Driving Navigation World Models](https://mlsanity.com/paper/2510.18313/) (2025)
- [Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method](https://mlsanity.com/paper/2510.22973/) (2025)
- [InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning](https://mlsanity.com/paper/2608.30657/) (2026)
- [Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images](https://mlsanity.com/paper/2607.01633/) (2026)
- [Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene Completion](https://mlsanity.com/paper/2511.12498/) (2025)
- [Adaptive Multi-Scale Channel-Spatial Attention Aggregation Framework for 3D Indoor Semantic Scene Completion Toward Assisting Visually Impaired](https://mlsanity.com/paper/2602.16385/) (2026)
- [ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction](https://mlsanity.com/paper/2604.01081/) (2026)
- [DualPathOcc: Dual-Resolution BEV Encoder for 3D Occupancy Prediction](https://mlsanity.com/paper/2609.06370/) (2026)

## Abstract (arXiv)

Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding complex 3D scenes from limited 2D image observations. Existing SOP methods typically aggregate contextual features to assist the occupancy representation learning, alleviating issues like occlusion or ambiguity. However, these solutions often face misalignment issues wherein the corresponding features at the same position across different frames may have different semantic meanings during the aggregation process, which leads to unreliable contextual fusion results and an unstable representation learning process. To address this problem, we introduce a new Hierarchical context alignment paradigm for a more accurate SOP (Hi-SOP). Hi-SOP first disentangles the geometric and temporal context for separate alignment, which two branches are then composed to enhance the reliability of SOP. This parsing of the visual input into a local-global alignment hierarchy includes: (I) disentangled geometric and temporal separate alignment, within each leverages depth confidence and camera pose as prior for relevant feature matching respectively; (II) global alignment and composition of the transformed geometric and temporal volumes based on semantics consistency. Our method outperforms SOTAs for semantic scene completion on the SemanticKITTI & NuScenes-Occupancy datasets and LiDAR semantic segmentation on the NuScenes dataset. The project website is available at https://arlo0o.github.io/hisop.github.io/.