TUNI: Real-time RGB-T Semantic Segmentation with Unified Multi-Modal Feature Extraction and Cross-Modal Feature Fusion

• URL: http://arxiv.org/abs/2509.10005v1
• Date: Fri, 12 Sep 2025 07:02:45 GMT
• Title: TUNI: Real-time RGB-T Semantic Segmentation with Unified Multi-Modal Feature Extraction and Cross-Modal Feature Fusion
• Authors: Xiaodong Guo, Tong Liu, Yike Li, Zi'ang Lin, Zhihong Deng,
• Abstract summary: RGB-thermal (RGB-T) semantic segmentation improves the environmental perception of autonomous platforms in challenging conditions.<n>Prevailing models employ encoders pre-trained on RGB images to extract features from both RGB and infrared inputs.<n>We propose TUNI, with an RGB-T encoder consisting of multiple stacked blocks that simultaneously perform multi-modal feature extraction and cross-modal fusion.
• Score: 11.878642970457646
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: RGB-thermal (RGB-T) semantic segmentation improves the environmental perception of autonomous platforms in challenging conditions. Prevailing models employ encoders pre-trained on RGB images to extract features from both RGB and infrared inputs, and design additional modules to achieve cross-modal feature fusion. This results in limited thermal feature extraction and suboptimal cross-modal fusion, while the redundant encoders further compromises the model's real-time efficiency. To address the above issues, we propose TUNI, with an RGB-T encoder consisting of multiple stacked blocks that simultaneously perform multi-modal feature extraction and cross-modal fusion. By leveraging large-scale pre-training with RGB and pseudo-thermal data, the RGB-T encoder learns to integrate feature extraction and fusion in a unified manner. By slimming down the thermal branch, the encoder achieves a more compact architecture. Moreover, we introduce an RGB-T local module to strengthen the encoder's capacity for cross-modal local feature fusion. The RGB-T local module employs adaptive cosine similarity to selectively emphasize salient consistent and distinct local features across RGB-T modalities. Experimental results show that TUNI achieves competitive performance with state-of-the-art models on FMB, PST900 and CART, with fewer parameters and lower computational cost. Meanwhile, it achieves an inference speed of 27 FPS on a Jetson Orin NX, demonstrating its real-time capability in deployment. Codes are available at https://github.com/xiaodonguo/TUNI.

Related papers

• HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detection [75.406055413928]
  We propose a novel prompt-driven segment anything model (HyPSAM) for RGB-T SOD.<n> DFNet employs dynamic convolution and multi-branch decoding to facilitate adaptive cross-modality interaction.<n>Experiments on three public datasets demonstrate that our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-09-23T07:32:11Z)
• Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection [67.02804741856512]
  We propose a novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection.<n>Our method introduces two key components: (1) a Mutual Multi-Modal Enhanced Block (MMEB), which fuses and enhances hierarchical RGB and IR feature maps in a coarse-to-fine manner, and (2) a Feature Alignment Block (FAB) that corrects misalignments between decoder outputs and IR feature maps by leveraging deformable convolutions.
  arXiv  Detail & Related papers  (2025-01-25T06:21:06Z)
• Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion [4.963745612929956]
  The main problem in RGB-T tracking is the correct and optimal merging of the cross-modal features of visible and thermal images.<n>CSTNet aims to achieve a direct fusion of cross-modal channels and spatial features in RGB-T tracking.<n>CSTNet and CSTNet-small achieve real-time speeds of 21 fps and 33 fps on the Nvidia Jetson Xavier.
  arXiv  Detail & Related papers  (2024-05-06T05:58:49Z)
• RGB-X Object Detection via Scene-Specific Fusion Modules [10.583691362114473]
  We present an efficient and modular RGB-X fusion network that can leverage and fuse pretrained single-modal models. Our experiments demonstrate the superiority of our method compared to existing works on RGB-thermal and RGB-gated datasets.
  arXiv  Detail & Related papers  (2023-10-30T09:27:31Z)
• Channel and Spatial Relation-Propagation Network for RGB-Thermal Semantic Segmentation [10.344060599932185]
  RGB-Thermal (RGB-T) semantic segmentation has shown great potential in handling low-light conditions. The key to RGB-T semantic segmentation is to effectively leverage the complementarity nature of RGB and thermal images.
  arXiv  Detail & Related papers  (2023-08-24T03:43:47Z)
• Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation [19.41334573257174]
  Traditional methods mostly use RGB images which are heavily affected by lighting conditions, eg, darkness. Recent studies show thermal images are robust to the night scenario as a compensating modality for segmentation. This work proposes a Residual Spatial Fusion Network (RSFNet) for RGB-T semantic segmentation.
  arXiv  Detail & Related papers  (2023-06-17T14:28:08Z)
• CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection [144.66411561224507]
  We present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement. Our network outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-10-06T11:59:19Z)
• 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)
• Transformer-based Network for RGB-D Saliency Detection [82.6665619584628]
  Key to RGB-D saliency detection is to fully mine and fuse information at multiple scales across the two modalities. We show that transformer is a uniform operation which presents great efficacy in both feature fusion and feature enhancement. Our proposed network performs favorably against state-of-the-art RGB-D saliency detection methods.
  arXiv  Detail & Related papers  (2021-12-01T15:53:58Z)
• Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection [78.47767202232298]
  We propose a novel Cross-modality Discrepant Interaction Network (CDINet) for RGB-D SOD. Two components are designed to implement the effective cross-modality interaction. Our network outperforms $15$ state-of-the-art methods both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2021-08-04T11:24:42Z)
• 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.