EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network

• URL: http://arxiv.org/abs/2406.07042v1
• Date: Tue, 11 Jun 2024 08:01:02 GMT
• Title: EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network
• Authors: Yining Shi, Kun Jiang, Ke Wang, Kangan Qian, Yunlong Wang, Jiusi Li, Tuopu Wen, Mengmeng Yang, Yiliang Xu, Diange Yang,
• Abstract summary: Existing 3D occupancy networks (occnets) are both computationally heavy and label-hungry. This paper proposes an efficient 3d occupancy network (EFFOcc) that targets the minimal network complexity and label requirement while achieving state-of-the-art accuracy.
• Score: 14.798733498419935
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D occupancy prediction (Occ) is a rapidly rising challenging perception task in the field of autonomous driving which represents the driving scene as uniformly partitioned 3D voxel grids with semantics. Compared to 3D object detection, grid perception has great advantage of better recognizing irregularly shaped, unknown category, or partially occluded general objects. However, existing 3D occupancy networks (occnets) are both computationally heavy and label-hungry. In terms of model complexity, occnets are commonly composed of heavy Conv3D modules or transformers on the voxel level. In terms of label annotations requirements, occnets are supervised with large-scale expensive dense voxel labels. Model and data inefficiency, caused by excessive network parameters and label annotations requirement, severely hinder the onboard deployment of occnets. This paper proposes an efficient 3d occupancy network (EFFOcc), that targets the minimal network complexity and label requirement while achieving state-of-the-art accuracy. EFFOcc only uses simple 2D operators, and improves Occ accuracy to the state-of-the-art on multiple large-scale benchmarks: Occ3D-nuScenes, Occ3D-Waymo, and OpenOccupancy-nuScenes. On Occ3D-nuScenes benchmark, EFFOcc has only 18.4M parameters, and achieves 50.46 in terms of mean IoU (mIoU), to our knowledge, it is the occnet with minimal parameters compared with related occnets. Moreover, we propose a two-stage active learning strategy to reduce the requirements of labelled data. Active EFFOcc trained with 6\% labelled voxels achieves 47.19 mIoU, which is 95.7% fully supervised performance. The proposed EFFOcc also supports improved vision-only occupancy prediction with the aid of region-decomposed distillation. Code and demo videos will be available at https://github.com/synsin0/EFFOcc.

Related papers

• ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding [51.509115746992165]
  We introduce ARKit LabelMaker, the first large-scale, real-world 3D dataset with dense semantic annotations. We also push forward the state-of-the-art performance on ScanNet and ScanNet200 dataset with prevalent 3D semantic segmentation models.
  arXiv  Detail & Related papers  (2024-10-17T14:44:35Z)
• OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity [11.287721740276048]
  3D semantic occupancy prediction networks have demonstrated remarkable capabilities in reconstructing the geometric and semantic structure of 3D scenes. We introduce OccRWKV, an efficient semantic occupancy network inspired by Receptance Weighted Key Value (RWKV) OccRWKV separates semantics, occupancy prediction, and feature fusion into distinct branches, each incorporating Sem-RWKV and Geo-RWKV blocks.
  arXiv  Detail & Related papers  (2024-09-30T06:27:50Z)
• Bayesian Self-Training for Semi-Supervised 3D Segmentation [59.544558398992386]
  3D segmentation is a core problem in computer vision. densely labeling 3D point clouds to employ fully-supervised training remains too labor intensive and expensive. Semi-supervised training provides a more practical alternative, where only a small set of labeled data is given, accompanied by a larger unlabeled set.
  arXiv  Detail & Related papers  (2024-09-12T14:54:31Z)
• Towards Label-free Scene Understanding by Vision Foundation Models [87.13117617056004]
  We investigate the potential of vision foundation models in enabling networks to comprehend 2D and 3D worlds without labelled data. We propose a novel Cross-modality Noisy Supervision (CNS) method that leverages the strengths of CLIP and SAM to supervise 2D and 3D networks simultaneously. Our 2D and 3D network achieves label-free semantic segmentation with 28.4% and 33.5% mIoU on ScanNet, improving 4.7% and 7.9%, respectively.
  arXiv  Detail & Related papers  (2023-06-06T17:57:49Z)
• Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving [34.368848580725576]
  We develop a label generation pipeline that produces dense, visibility-aware labels for any given scene. This pipeline comprises three stages: voxel densification, reasoning, and image-guided voxel refinement. We propose a new model, dubbed Coarse-to-Fine Occupancy (CTF-Occ) network, which demonstrates superior performance on the Occ3D benchmarks.
  arXiv  Detail & Related papers  (2023-04-27T17:40:08Z)
• OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction [16.66987810790077]
  OccFormer is a dual-path transformer network to process the 3D volume for semantic occupancy prediction. It achieves a long-range, dynamic, and efficient encoding of the camera-generated 3D voxel features.
  arXiv  Detail & Related papers  (2023-04-11T16:15:50Z)
• UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation [93.88170217725805]
  We propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features. Our evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-12-08T18:59:57Z)
• SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation [65.4396959244269]
  The paper tackles the challenge by designing a general framework to construct 3D learning architectures. The proposed approach can be applied to general backbones like PointNet and DGCNN. Experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation, and accuracy.
  arXiv  Detail & Related papers  (2022-09-13T12:12:19Z)
• 3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models [17.487852393066458]
  Existing verification method for point cloud model is time-expensive and computationally unattainable on large networks. We propose 3DVerifier to tackle both challenges by adopting a linear relaxation function to bound the multiplication layer and combining forward and backward propagation. Our approach achieves an orders-of-magnitude improvement in verification efficiency for the large network, and the obtained certified bounds are also significantly tighter than the state-of-the-art verifiers.
  arXiv  Detail & Related papers  (2022-07-15T15:31:16Z)
• End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection [62.34374949726333]
  Pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. We introduce a new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end.
  arXiv  Detail & Related papers  (2020-04-07T02:18:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.