Pith. sign in

REVIEW 9 cited by

OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion

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 2302.13540 v1 pith:37K7A5M4 submitted 2023-02-27 cs.CV

Ruihang Miao , Weizhou Liu , Mingrui Chen , Zheng Gong , Weixin Xu , Chen Hu , Shuchang Zhou This is my paper
classification cs.CV
keywords imagesmethodstereodepthoccdepthscenedepth-awaremiou
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

3D Semantic Scene Completion (SSC) can provide dense geometric and semantic scene representations, which can be applied in the field of autonomous driving and robotic systems. It is challenging to estimate the complete geometry and semantics of a scene solely from visual images, and accurate depth information is crucial for restoring 3D geometry. In this paper, we propose the first stereo SSC method named OccDepth, which fully exploits implicit depth information from stereo images (or RGBD images) to help the recovery of 3D geometric structures. The Stereo Soft Feature Assignment (Stereo-SFA) module is proposed to better fuse 3D depth-aware features by implicitly learning the correlation between stereo images. In particular, when the input are RGBD image, a virtual stereo images can be generated through original RGB image and depth map. Besides, the Occupancy Aware Depth (OAD) module is used to obtain geometry-aware 3D features by knowledge distillation using pre-trained depth models. In addition, a reformed TartanAir benchmark, named SemanticTartanAir, is provided in this paper for further testing our OccDepth method on SSC task. Compared with the state-of-the-art RGB-inferred SSC method, extensive experiments on SemanticKITTI show that our OccDepth method achieves superior performance with improving +4.82% mIoU, of which +2.49% mIoU comes from stereo images and +2.33% mIoU comes from our proposed depth-aware method. Our code and trained models are available at https://github.com/megvii-research/OccDepth.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency

    cs.CV 2025-07 conditional novelty 7.0 of 10

    PacGDC synthesizes diverse pseudo training geometries by rescaling depth predictions from foundation models, improving zero-shot and few-shot generalization of depth completion.

  2. Any to Full: Prompting Depth Anything for Depth Completion in One Stage

    cs.CV 2026-03 accept novelty 6.5 of 10

    Any2Full reformulates depth completion as one-stage scale-prompting of a pretrained monocular depth estimator, yielding domain-general, pattern-agnostic dense metric depth with lower error and higher speed than prior methods.

  3. QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy

    cs.CV 2025-11 conditional novelty 6.0 of 10

    Query-based 4D supervision with a contractive BEV representation sets a new state of the art for self-supervised 3D semantic occupancy from cameras.

  4. Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A dual-stream BEV architecture that separates instance and scene class queries achieves state-of-the-art mIoU of 17.35 on SemanticKITTI and 20.55 on SSCBench-KITTI-360.

  5. Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SceneDINO performs semantic scene completion from a single image in a fully unsupervised way by lifting self-supervised DINO features into a 3D feature field trained with multi-view consistency.

  6. VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A training-only Gaussian splatting loss, which renders predicted 3D semantics and motion into 2D camera views, improves semantic occupancy and scene flow prediction across several camera-based models.

  7. 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.

  8. GaussianFusionOcc: A Seamless Sensor Fusion Approach for 3D Occupancy Prediction Using 3D Gaussians

    cs.CV 2025-07 conditional novelty 5.0 of 10

    GaussianFusionOcc fuses camera, LiDAR, and radar features through deformable attention to refine semantic 3D Gaussians, improving 3D occupancy prediction on nuScenes while lowering memory use and latency.

  9. SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels

    cs.CV 2025-05 reject novelty 5.0 of 10

    SHTOcc combines attention-based sparse voxel selection with decoupled classifier retraining for 3D occupancy prediction, reporting efficiency gains and small, partly inconsistent accuracy improvements.

Pith tools