Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a novel semantic splatting approach based on Gaussian Splatting to achieve efficient and low-latency. Our method projects the RGB attributes and semantic features of point clouds onto the image plane, simultaneously rendering RGB images and semantic segmentation results. Leveraging the explicit structure of point clouds and a one-time rendering strategy, our approach significantly enhances efficiency during optimization and rendering. Additionally, we employ SAM2 to generate pseudo-labels for boundary regions, which often lack sufficient supervision, and introduce two-level aggregation losses at the 2D feature map and 3D spatial levels to improve the view-consistent and spatial continuity.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 56 of its 73 references that are in the map. First posted on arXiv 8 Dec 2024.
Builds on
56 of 73 references.
References · 56
- 2017Attention Is All You Needcited by 60,361
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2023Segment Anythingcited by 8,234
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
38 more
- 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
- 2018Dual Attention Network for Scene Segmentationcited by 1,003
- 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
- 2021Segmenter: Transformer for Semantic Segmentationcited by 855
- 2019Panoptic Feature Pyramid Networkscited by 645
- 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
- 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 415
- 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
- 2023Segment Anything in High Qualitycited by 376
- 2021Remote Sensing Image Change Detection with Transformerscited by 306
- 2023Text-to-3D using Gaussian Splattingcited by 299
- 2023Segment Anything Model for Medical Image Analysis: an Experimental Studycited by 291
- 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
- 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
- 2023Transformer-Based Visual Segmentation: A Surveycited by 124
- 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
- 2021MISSFormer: An Effective Medical Image Segmentation Transformercited by 103
- 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
- 2024Not All Noises Are Created Equally:Diffusion Noise Selection and Optimizationcited by 71
- 2024OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Viewscited by 69
- 2018HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentationcited by 66
- 2023Segment Anything in 3D with Radiance Fieldscited by 62
- 2020MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understandingcited by 59
- 2023C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detectioncited by 58
- 2024Click-Gaussian: Interactive Segmentation to Any 3D Gaussianscited by 58
- 2024FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimallycited by 58
- 2017CNN-based Segmentation of Medical Imaging Datacited by 48
- 2024CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detectioncited by 48
- 2024GSEdit: Efficient Text-Guided Editing of 3D Objects via Gaussian Splattingcited by 37
- 2024RSCaMa: Remote Sensing Image Change Captioning with State Space Modelcited by 35
- 2018Feature Pyramid Network for Multi-Class Land Segmentationcited by 24
- 2023Interactive Segment Anything NeRF with Feature Imitationcited by 24
- 2022Unsupervised Multi-View Object Segmentation Using Radiance Field Propagationcited by 22
- 2023GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understandingcited by 20
- 2024Application of 3D Gaussian Splatting for Cinematic Anatomy on Consumer Class Devicescited by 17
- 2023Pixel-Level Change Detection Pseudo-Label Learning for Remote Sensing Change Captioningcited by 14
- 2023PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenescited by 10
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.