ATT-CR: Adaptive Triangular Transformer for Cloud Removal

• URL: http://arxiv.org/abs/2606.05999v1
• Date: Thu, 04 Jun 2026 10:47:41 GMT
• Title: ATT-CR: Adaptive Triangular Transformer for Cloud Removal
• Abstract summary: Cloud removal aims to accurately reconstruct the ground objects obscured by clouds in remote sensing images.<n>Existing Transformer-based methods have shown impressive results by effectively modeling long-range dependencies in cloudy images.<n>We propose the Adaptive Triangular Transformer for Cloud Removal (ATT-CR), a model that effectively reduces computational costs and mitigates interference from cloudy pixels.
• Score: 17.828250974983515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cloud removal aims to accurately reconstruct the ground objects obscured by clouds in remote sensing images. Existing Transformer-based methods utilizing self-attention have shown impressive results by effectively modeling long-range dependencies in cloudy images. However, they suffer from the following issues: 1) the high computational complexity of self-attention limits scalability; 2) treating both cloudy and clean pixels as valid within the attention computation brings disturbances in subsequent layers, leading to suboptimal performance. To address these challenges, we propose the Adaptive Triangular Transformer for Cloud Removal (ATT-CR), a model that effectively reduces computational costs and mitigates interference from cloudy pixels. Specifically, it consists of two core components: Triangular Attention (TAN) and Feature Selected Gating Module (FSGM). TAN employs lower and upper triangular matrices to approximate Softmax attention with O(N) computational complexity, significantly reducing the computational costs. The FSGM, on the other hand, integrates with TAN to adaptively distinguish between cloudy and clean features, which minimizes the introduction of invalid information into subsequent layers. Extensive experiments on cloud removal benchmarks demonstrate that ATT-CR delivers superior performance compared to existing methods.

Related papers

• Tri-Efficient Transfer Learning for Point Cloud Videos [32.14641034344552]
  PoinTriE aims to mine richer supervision signals from existing data rather than blindly scaling datasets.<n>For pre-training, pseudo-motion trajectories are synthesized via rigid transformations, paired with text corpora and 2D projections derived from raw point clouds.<n>During fine-tuning, we freeze the pretrained backbone and only update a lightweight Spatio-temporal Side Network built with LoRA units.
  arXiv  Detail & Related papers  (2026-06-23T05:55:02Z)
• When Cloud Removal Meets Diffusion Model in Remote Sensing [4.824120664293887]
  We propose DC4CR (Diffusion Control for Cloud Removal), a novel framework for cloud removal in remote sensing imagery.<n>Our method introduces prompt-driven control, allowing selective removal of thin and thick clouds without relying on pre-generated cloud masks.<n>Experiments on the RICE and CUHK-CR datasets demonstrate state-of-the-art performance, achieving superior cloud removal across diverse conditions.
  arXiv  Detail & Related papers  (2025-04-21T00:56:57Z)
• Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformer [52.40992954884257]
  3D visualization techniques have fundamentally transformed how we interact with digital content.<n>Massive data size of point clouds presents significant challenges in data compression.<n>We propose an end-to-end deep learning framework that seamlessly integrates PCAC with differentiable rendering.
  arXiv  Detail & Related papers  (2024-11-12T16:12:51Z)
• Tackling fluffy clouds: robust field boundary delineation across global agricultural landscapes with Sentinel-1 and Sentinel-2 Time Series [1.0251998687197121]
  We introduce PTAViT3D, a deep learning architecture specifically designed for processing three-dimensional time series satellite imagery.<n>We also present PTAViT3D-CA, an extension to the PTAViT3D model incorporating cross-attention mechanisms to fuse S1 and S2 datasets.<n>Our results consistently demonstrate state-of-the-art performance, highlighting excellent global transferability and robustness.
  arXiv  Detail & Related papers  (2024-09-20T15:10:04Z)
• DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection [42.07920565812081]
  We propose a novel post-training weight pruning scheme for 3D object detection. It determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence. This framework aims to minimize detection distortion of network output to maximally maintain detection precision.
  arXiv  Detail & Related papers  (2024-07-02T09:33:32Z)
• Look-Around Before You Leap: High-Frequency Injected Transformer for Image Restoration [46.96362010335177]
  In this paper, we propose HIT, a simple yet effective High-frequency Injected Transformer for image restoration. Specifically, we design a window-wise injection module (WIM), which incorporates abundant high-frequency details into the feature map, to provide reliable references for restoring high-quality images. In addition, we introduce a spatial enhancement unit (SEU) to preserve essential spatial relationships that may be lost due to the computations carried out across channel dimensions in the BIM.
  arXiv  Detail & Related papers  (2024-03-30T08:05:00Z)
• IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images [55.40601468843028]
  We present an iterative diffusion process for cloud removal (IDF-CR) IDF-CR is divided into two-stage models that address pixel space and latent space. In the latent space stage, the diffusion model transforms low-quality cloud removal into high-quality clean output.
  arXiv  Detail & Related papers  (2024-03-18T15:23:48Z)
• Adaptive Point Transformer [88.28498667506165]
  Adaptive Point Cloud Transformer (AdaPT) is a standard PT model augmented by an adaptive token selection mechanism. AdaPT dynamically reduces the number of tokens during inference, enabling efficient processing of large point clouds.
  arXiv  Detail & Related papers  (2024-01-26T13:24:45Z)
• SG-GAN: Fine Stereoscopic-Aware Generation for 3D Brain Point Cloud Up-sampling from a Single Image [15.698577360754877]
  A novel model named stereoscopic-aware graph generative adversarial network (SG-GAN) is proposed to generate fine high-density brain point clouds.<n>The model shows superior performance in terms of visual quality, objective measurements, and performance in classification.
  arXiv  Detail & Related papers  (2023-05-22T02:42:12Z)
• CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning [81.85951026033787]
  We set transformers in this work and incorporate them into a hierarchical framework for shape classification and part and scene segmentation. We also compute efficient and dynamic global cross attentions by leveraging sampling and grouping at each iteration. The proposed hierarchical model achieves state-of-the-art shape classification in mean accuracy and yields results on par with the previous segmentation methods.
  arXiv  Detail & Related papers  (2022-07-31T21:39:15Z)
• Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision [68.35777836993212]
  We propose a Pseudo-LiDAR point cloud network to generate temporally and spatially high-quality point cloud sequences. By exploiting the scene flow between point clouds, the proposed network is able to learn a more accurate representation of the 3D spatial motion relationship.
  arXiv  Detail & Related papers  (2020-06-20T03:11:04Z)

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.