# VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection

arXiv: https://arxiv.org/abs/2506.04623 · HTML: https://mlsanity.com/paper/2506.04623/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 86 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 30 of 71)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [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)
- [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)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation](https://mlsanity.com/paper/2406.02918/) (2024)

## Built on by (most cited first, 13 of 13)

- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [RAP: 3D Rasterization Augmented End-to-End Planning](https://mlsanity.com/paper/2510.04333/) (2025)
- [Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robots](https://mlsanity.com/paper/2603.13108/) (2026)
- [Large Depth Completion Model from Sparse Observations](https://mlsanity.com/paper/2605.30115/) (2026)
- [Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction](https://mlsanity.com/paper/2507.18331/) (2025)
- [Can we Trust Unreliable Voxels? Exploring 3D Semantic Occupancy Prediction under Label Noise](https://mlsanity.com/paper/2603.06279/) (2026)
- [Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models](https://mlsanity.com/paper/2605.15424/) (2026)
- [VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understanding](https://mlsanity.com/paper/2605.25059/) (2026)
- [MetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopy](https://mlsanity.com/paper/2508.03596/) (2025)
- [ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction](https://mlsanity.com/paper/2604.01081/) (2026)
- [Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation](https://mlsanity.com/paper/2605.28587/) (2026)
- [Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute](https://mlsanity.com/paper/2608.06014/) (2026)
- [SelectOccFlow: Selective Spatiotemporal Aggregation for 3D Occupancy and Scene Flow Prediction](https://mlsanity.com/paper/2610.04356/) (2026)

## Abstract (arXiv)

3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate it as a dense segmentation task, independently classifying each voxel. However, this paradigm neglects critical instance-centric discriminability, leading to instance-level incompleteness and adjacent ambiguities. To address this, we highlight a free lunch of occupancy labels: the voxel-level class label implicitly provides insight at the instance level, which is overlooked by the community. Motivated by this observation, we first introduce a training-free Voxel-to-Instance (VoxNT) trick: a simple yet effective method that freely converts voxel-level class labels into instance-level offset labels. Building on this, we further propose VoxDet, an instance-centric framework that reformulates the voxel-level occupancy prediction as dense object detection by decoupling it into two sub-tasks: offset regression and semantic prediction. Specifically, based on the lifted 3D volume, VoxDet first uses (a) Spatially-decoupled Voxel Encoder to generate disentangled feature volumes for the two sub-tasks, which learn task-specific spatial deformation in the densely projected tri-perceptive space. Then, we deploy (b) Task-decoupled Dense Predictor to address this task via dense detection. Here, we first regress a 4D offset field to estimate distances (6 directions) between voxels and object borders in the voxel space. The regressed offsets are then used to guide the instance-level aggregation in the classification branch, achieving instance-aware prediction. Experiments show that VoxDet can be deployed on both camera and LiDAR input, jointly achieving state-of-the-art results on both benchmarks. VoxDet is not only highly efficient, but also achieves 63.0 IoU on the SemanticKITTI test set, ranking 1st on the online leaderboard.