GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision

• URL: http://arxiv.org/abs/2405.10591v1
• Date: Fri, 17 May 2024 07:31:20 GMT
• Title: GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision
• Authors: Xin Tan, Wenbin Wu, Zhiwei Zhang, Chaojie Fan, Yong Peng, Zhizhong Zhang, Yuan Xie, Lizhuang Ma,
• Abstract summary: This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
• Score: 49.839374549646884
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D occupancy perception holds a pivotal role in recent vision-centric autonomous driving systems by converting surround-view images into integrated geometric and semantic representations within dense 3D grids. Nevertheless, current models still encounter two main challenges: modeling depth accurately in the 2D-3D view transformation stage, and overcoming the lack of generalizability issues due to sparse LiDAR supervision. To address these issues, this paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach is three-fold: 1) Integration of explicit lift-based depth prediction and implicit projection-based transformers for depth modeling, enhancing the density and robustness of view transformation. 2) Utilization of mask-based encoder-decoder architecture for fine-grained semantic predictions; 3) Adoption of context-aware self-training loss functions in the pertaining stage to complement LiDAR supervision, involving the re-rendering of 2D depth maps from 3D occupancy features and leveraging image reconstruction loss to obtain denser depth supervision besides sparse LiDAR ground-truths. Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone compared with current models, marking an improvement of 3.3% due to our proposed contributions. Comprehensive experimentation also demonstrates the consistent superiority of our method over baselines and alternative approaches.

Related papers

• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments [77.0399450848749]
  We propose an OccNeRF method for training occupancy networks without 3D supervision. We parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range. For semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model.
  arXiv  Detail & Related papers  (2023-12-14T18:58:52Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios [0.0]
  We propose OCTraN, a transformer architecture that uses iterative-attention to convert 2D image features into 3D occupancy features. We also develop a self-supervised training pipeline to generalize the model to any scene by eliminating the need for LiDAR ground truth.
  arXiv  Detail & Related papers  (2023-07-20T15:06:44Z)
• Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's Eye View [44.78243406441798]
  This paper focuses on leveraging geometry information, such as depth, to model such feature transformation. We first lift the 2D image features to the 3D space defined for the ego vehicle via a predicted parametric depth distribution for each pixel in each view. We then aggregate the 3D feature volume based on the 3D space occupancy derived from depth to the BEV frame.
  arXiv  Detail & Related papers  (2023-07-09T06:07:22Z)
• High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
  We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views. Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
  arXiv  Detail & Related papers  (2022-11-28T18:59:52Z)
• MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection [10.377424252002792]
  monocular 3D object detection lacks accurate depth recovery ability. Deep neural network (DNN) enables monocular depth-sensing from high-level learned features. We propose a joint semantic and geometric cost volume to model the depth error.
  arXiv  Detail & Related papers  (2022-03-16T11:54:10Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• A Novel 3D-UNet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimation [0.45880283710344055]
  Bilateral Grid based 3D convolutional neural network, dubbed as 3DBG-UNet, parameterizes high dimensional feature space by encoding compact 3D bilateral grids with UNets. Another novel 3DBGES-UNet model is introduced that integrate 3DBG-UNet for inferring an accurate depth map given a single color view.
  arXiv  Detail & Related papers  (2021-05-21T04:53:14Z)

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.