Pith. sign in

REVIEW 12 cited by

OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.03991 v1 pith:PANKMYES submitted 2023-03-07 cs.CV

Xiaofeng Wang , Zheng Zhu , Wenbo Xu , Yunpeng Zhang , Yi Wei , Xu Chi , Yun Ye , Dalong Du
show 2 more authors
Jiwen Lu Xingang Wang
This is my paper · ORCID
classification cs.CV
keywords occupancyperceptionbenchmarkopenoccupancysurroundingsemanticannotationsalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Semantic occupancy perception is essential for autonomous driving, as automated vehicles require a fine-grained perception of the 3D urban structures. However, existing relevant benchmarks lack diversity in urban scenes, and they only evaluate front-view predictions. Towards a comprehensive benchmarking of surrounding perception algorithms, we propose OpenOccupancy, which is the first surrounding semantic occupancy perception benchmark. In the OpenOccupancy benchmark, we extend the large-scale nuScenes dataset with dense semantic occupancy annotations. Previous annotations rely on LiDAR points superimposition, where some occupancy labels are missed due to sparse LiDAR channels. To mitigate the problem, we introduce the Augmenting And Purifying (AAP) pipeline to ~2x densify the annotations, where ~4000 human hours are involved in the labeling process. Besides, camera-based, LiDAR-based and multi-modal baselines are established for the OpenOccupancy benchmark. Furthermore, considering the complexity of surrounding occupancy perception lies in the computational burden of high-resolution 3D predictions, we propose the Cascade Occupancy Network (CONet) to refine the coarse prediction, which relatively enhances the performance by ~30% than the baseline. We hope the OpenOccupancy benchmark will boost the development of surrounding occupancy perception algorithms.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction

    cs.CV 2026-07 conditional novelty 7.0 of 10

    Factorized Dense Routing approximates unconstrained 2D-to-3D feature mixing by hierarchical tensor contractions, yielding global-context occupancy prediction that remains robust without camera extrinsics.

  2. VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    VISA improves closed-set 3D occupancy mIoU on nuScenes by using VLM instance audits as reliability-weighted semantic supervisors during training of existing world models.

  3. GaussianSeed: Hierarchical Gaussian Seeding for High-Resolution 3D Occupancy Prediction

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A hierarchical Gaussian occupancy representation with regression-based seeding predicts high-resolution 3D occupancy at lower latency than prior sparse baselines, validated on nuScenes and a new 0.1m campus dataset.

  4. Semantic Causality-Aware Vision-Based 3D Occupancy Prediction

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A class-conditional gradient loss (Causal Loss) plus channel-grouped lifting, learnable camera offsets, and normalized convolution raises Occ3D mIoU by 1.2/0.8 points and cuts the camera-noise mIoU drop from 32% to 7%.

  5. Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction

    cs.CV 2025-04 conditional novelty 6.0 of 10

    GDFusion fuses scene, motion, and geometry cues through gradient-descent-style RNN updates, improving mIoU by 1.4 to 4.8 points on Occ3D while cutting inference memory by 27 to 72 percent.

  6. An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training

    cs.CV 2024-12 conditional novelty 6.0 of 10

    An end-to-end, non-autoregressive 3D occupancy world model warps dynamic voxels via predicted flow, moves static voxels by pose, and uses image-based rendering supervision, achieving state-of-the-art results on three ...

  7. Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection

    cs.CV 2024-12 conditional novelty 6.0 of 10

    An object-centric occupancy completion network, trained on a new annotation pipeline, improves 3D shape completion and detection on the Waymo Open Dataset.

  8. EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding

    cs.CV 2024-12 conditional novelty 6.0 of 10

    EmbodiedOcc maintains an explicit global Gaussian memory that is progressively updated from monocular RGB frames, and it introduces a reorganized ScanNet benchmark for embodied 3D occupancy prediction.

  9. GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    GTAD combines an in-model latent denoising network with global temporal interaction to improve camera-based 3D semantic occupancy prediction, reporting 40.76 mIoU on Occ3D-nuScenes at 12 epochs.

  10. QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction

    cs.CV 2025-06 conditional novelty 5.0 of 10

    QuadricFormer represents 3D scenes as a probabilistic mixture of superquadrics, improving accuracy and efficiency over Gaussian-based occupancy prediction on nuScenes.

  11. GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A world model operating on 3D Gaussians forecasts the current occupancy from the previous frame and current RGB, improving mIoU by about 2 points on nuScenes without meaningful added latency.

  12. GaussianAD: Gaussian-Centric End-to-End Autonomous Driving

    cs.CV 2024-12 conditional novelty 5.0 of 10

    GaussianAD uses sparse 3D semantic Gaussians as the intermediate representation for camera-only end-to-end driving, adding Gaussian flow prediction and future-scene supervision to achieve strong open-loop planning res...

Pith tools