CSIPlab / MMSFormerLinks
We propose a novel fusion strategy that can effectively fuse information from different modality combinations. We also propose a new model named Multi-Modal Segmentation TransFormer (MMSFormer) that incorporates the proposed fusion strategy to perform multimodal material and semantic segmentation tasks.
☆31Updated last year
Alternatives and similar repositories for MMSFormer
Users that are interested in MMSFormer are comparing it to the libraries listed below
Sorting:
- Official Implementation of Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling☆194Updated 2 months ago
- Repository of DELIVER dataset and CMNeXt models (CVPR 2023)☆200Updated last year
- ☆34Updated 11 months ago
- Code for UAED and MuGE☆92Updated 10 months ago
- ☆92Updated last year
- ☆68Updated 2 years ago
- Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).☆76Updated 7 months ago
- Code for PID: Physics-Informed Diffusion Model for Infrared Image Generation☆152Updated 4 months ago
- CVPR2024 Frequency-Adaptive Dilated Convolution☆38Updated last year
- The official implementation of "Segment Anything with Multiple Modalities".☆110Updated last year
- ☆22Updated 7 months ago
- ☆70Updated 3 years ago
- [Arxiv 2025] DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding☆66Updated 2 months ago
- The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.☆122Updated 7 months ago
- Vision Mamba: A Comprehensive Survey and Taxonomy☆99Updated last year
- CVPR 2025 | Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond☆93Updated 2 months ago
- Dataset & Code for ACM Multimedia 2023 paper. "SemanticRT: A Large-Scale Dataset and Method for Robust Semantic Segmentation in Multispec…☆14Updated 9 months ago
- Official implementation of the CVPR 2024 paper "Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling"☆23Updated last year
- (ICCV'23) Learning to Upsample by Learning to Sample☆183Updated last year
- ☆51Updated last year
- GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model [CVPR -2025]☆131Updated 10 months ago
- ☆63Updated 2 years ago
- Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation☆51Updated 5 months ago
- [IEEE TPAMI'25] Low-Resolution Self-Attention For Semantic Segmentation☆67Updated 7 months ago
- ☆209Updated last year
- ☆77Updated last year
- [ECCV2024 - Oral] Adaptive Parametric Activation☆54Updated 2 months ago
- ☆133Updated 3 years ago
- [ICLR 2025] SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement☆82Updated 9 months ago
- ICLR2024 When Sementic Segmentation Meets Frequency Aliasing☆46Updated last year