RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion

• URL: http://arxiv.org/abs/2407.21631v2
• Date: Thu, 22 Aug 2024 07:42:14 GMT
• Title: RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion
• Authors: Jianxin Huang, Jiahang Li, Ning Jia, Yuxiang Sun, Chengju Liu, Qijun Chen, Rui Fan,
• Abstract summary: RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps. RoadFormer+ represents additional types/modalities of data such as depth, thermal, surface normal, and polarization. RoadFormer+ ranks first on the KITTI Road benchmark and achieves state-of-the-art performance in mean intersection over union.
• Score: 23.08593450089786
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and fuses these features through attention mechanisms, demonstrating compelling efficacy in RGB-Normal road scene parsing. However, its performance significantly deteriorates when handling other types/sources of data or performing more universal, all-category scene parsing tasks. To overcome these limitations, this study introduces RoadFormer+, an efficient, robust, and adaptable model capable of effectively fusing RGB-X data, where ``X'', represents additional types/modalities of data such as depth, thermal, surface normal, and polarization. Specifically, we propose a novel hybrid feature decoupling encoder to extract heterogeneous features and decouple them into global and local components. These decoupled features are then fused through a dual-branch multi-scale heterogeneous feature fusion block, which employs parallel Transformer attentions and convolutional neural network modules to merge multi-scale features across different scales and receptive fields. The fused features are subsequently fed into a decoder to generate the final semantic predictions. Notably, our proposed RoadFormer+ ranks first on the KITTI Road benchmark and achieves state-of-the-art performance in mean intersection over union on the Cityscapes, MFNet, FMB, and ZJU datasets. Moreover, it reduces the number of learnable parameters by 65\% compared to RoadFormer. Our source code will be publicly available at mias.group/RoadFormerPlus.

Related papers

• Homography Guided Temporal Fusion for Road Line and Marking Segmentation [73.47092021519245]
  Road lines and markings are frequently occluded in the presence of moving vehicles, shadow, and glare. We propose a Homography Guided Fusion (HomoFusion) module to exploit temporally-adjacent video frames for complementary cues. We show that exploiting available camera intrinsic data and ground plane assumption for cross-frame correspondence can lead to a light-weight network with significantly improved performances in speed and accuracy.
  arXiv  Detail & Related papers  (2024-04-11T10:26:40Z)
• HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion [15.538174593176166]
  In this study, we explore a feasible strategy to fully exploit VFM features for RGB-thermal scene parsing. Specifically, we design a hybrid, asymmetric encoder that incorporates both a VFM and a convolutional neural network. This design allows for more effective extraction of complementary heterogeneous features, which are subsequently fused in a dual-path, progressive manner.
  arXiv  Detail & Related papers  (2024-04-04T15:31:11Z)
• RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing [17.118074007418123]
  RoadFormer is a Transformer-based data-fusion network developed for road scene parsing. RoadFormer outperforms all other state-of-the-art networks for road scene parsing.
  arXiv  Detail & Related papers  (2023-09-19T06:32:19Z)
• Mutual-Guided Dynamic Network for Image Fusion [51.615598671899335]
  We propose a novel mutual-guided dynamic network (MGDN) for image fusion, which allows for effective information utilization across different locations and inputs. Experimental results on five benchmark datasets demonstrate that our proposed method outperforms existing methods on four image fusion tasks.
  arXiv  Detail & Related papers  (2023-08-24T03:50:37Z)
• HODINet: High-Order Discrepant Interaction Network for RGB-D Salient Object Detection [4.007827908611563]
  RGB-D salient object detection (SOD) aims to detect the prominent regions by jointly modeling RGB and depth information. Most RGB-D SOD methods apply the same type of backbones and fusion modules to identically learn the multimodality and multistage features. In this paper, we propose a high-order discrepant interaction network (HODINet) for RGB-D SOD.
  arXiv  Detail & Related papers  (2023-07-03T11:56:21Z)
• Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detection [67.33924278729903]
  In this work, we propose Dual Swin-Transformer based Mutual Interactive Network. We adopt Swin-Transformer as the feature extractor for both RGB and depth modality to model the long-range dependencies in visual inputs. Comprehensive experiments on five standard RGB-D SOD benchmark datasets demonstrate the superiority of the proposed DTMINet method.
  arXiv  Detail & Related papers  (2022-06-07T08:35:41Z)
• SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection [12.126413875108993]
  We propose a cross-modality fusion model SwinNet for RGB-D and RGB-T salient object detection. The proposed model outperforms the state-of-the-art models on RGB-D and RGB-T datasets.
  arXiv  Detail & Related papers  (2022-04-12T07:37:39Z)
• MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking [72.65494220685525]
  We propose a new dynamic modality-aware filter generation module (named MFGNet) to boost the message communication between visible and thermal data. We generate dynamic modality-aware filters with two independent networks. The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively. To address issues caused by heavy occlusion, fast motion, and out-of-view, we propose to conduct a joint local and global search by exploiting a new direction-aware target-driven attention mechanism.
  arXiv  Detail & Related papers  (2021-07-22T03:10:51Z)
• Self-Supervised Representation Learning for RGB-D Salient Object Detection [93.17479956795862]
  We use Self-Supervised Representation Learning to design two pretext tasks: the cross-modal auto-encoder and the depth-contour estimation. Our pretext tasks require only a few and un RGB-D datasets to perform pre-training, which make the network capture rich semantic contexts. For the inherent problem of cross-modal fusion in RGB-D SOD, we propose a multi-path fusion module.
  arXiv  Detail & Related papers  (2021-01-29T09:16:06Z)
• Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation [59.94819184452694]
  Depth information has proven to be a useful cue in the semantic segmentation of RGBD images for providing a geometric counterpart to the RGB representation. Most existing works simply assume that depth measurements are accurate and well-aligned with the RGB pixels and models the problem as a cross-modal feature fusion. In this paper, we propose a unified and efficient Crossmodality Guided to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively.
  arXiv  Detail & Related papers  (2020-07-17T18:35:24Z)

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.