SDformer: Efficient End-to-End Transformer for Depth Completion

• URL: http://arxiv.org/abs/2409.08159v1
• Date: Thu, 12 Sep 2024 15:52:08 GMT
• Title: SDformer: Efficient End-to-End Transformer for Depth Completion
• Authors: Jian Qian, Miao Sun, Ashley Lee, Jie Li, Shenglong Zhuo, Patrick Yin Chiang,
• Abstract summary: Depth completion aims to predict dense depth maps with sparse depth measurements from a depth sensor. Currently, Convolutional Neural Network (CNN) based models are the most popular methods applied to depth completion tasks. To overcome the drawbacks of CNNs, a more effective and powerful method has been presented, which is an adaptive self-attention setting sequence-to-sequence model.
• Score: 5.864200786548098
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Depth completion aims to predict dense depth maps with sparse depth measurements from a depth sensor. Currently, Convolutional Neural Network (CNN) based models are the most popular methods applied to depth completion tasks. However, despite the excellent high-end performance, they suffer from a limited representation area. To overcome the drawbacks of CNNs, a more effective and powerful method has been presented: the Transformer, which is an adaptive self-attention setting sequence-to-sequence model. While the standard Transformer quadratically increases the computational cost from the key-query dot-product of input resolution which improperly employs depth completion tasks. In this work, we propose a different window-based Transformer architecture for depth completion tasks named Sparse-to-Dense Transformer (SDformer). The network consists of an input module for the depth map and RGB image features extraction and concatenation, a U-shaped encoder-decoder Transformer for extracting deep features, and a refinement module. Specifically, we first concatenate the depth map features with the RGB image features through the input model. Then, instead of calculating self-attention with the whole feature maps, we apply different window sizes to extract the long-range depth dependencies. Finally, we refine the predicted features from the input module and the U-shaped encoder-decoder Transformer module to get the enriching depth features and employ a convolution layer to obtain the dense depth map. In practice, the SDformer obtains state-of-the-art results against the CNN-based depth completion models with lower computing loads and parameters on the NYU Depth V2 and KITTI DC datasets.

Related papers

• Pixel-Aligned Multi-View Generation with Depth Guided Decoder [86.1813201212539]
  We propose a novel method for pixel-level image-to-multi-view generation. Unlike prior work, we incorporate attention layers across multi-view images in the VAE decoder of a latent video diffusion model. Our model enables better pixel alignment across multi-view images.
  arXiv  Detail & Related papers  (2024-08-26T04:56:41Z)
• Mask-adaptive Gated Convolution and Bi-directional Progressive Fusion Network for Depth Completion [3.8558637038709622]
  We propose a new model for depth completion based on an encoder-decoder structure. Our model introduces two key components: the Mask-adaptive Gated Convolution architecture and the Bi-directional Progressive Fusion module. We achieve remarkable performance in completing depth maps and outperformed existing approaches in terms of accuracy and reliability.
  arXiv  Detail & Related papers  (2024-01-15T02:58:06Z)
• CompletionFormer: Depth Completion with Convolutions and Vision Transformers [0.0]
  This paper proposes a Joint Convolutional Attention and Transformer block (JCAT), which deeply couples the convolutional attention layer and Vision Transformer into one block, as the basic unit to construct our depth completion model in a pyramidal structure. Our CompletionFormer outperforms state-of-the-art CNNs-based methods on the outdoor KITTI Depth Completion benchmark and indoor NYUv2 dataset, achieving significantly higher efficiency (nearly 1/3 FLOPs) compared to pure Transformer-based methods.
  arXiv  Detail & Related papers  (2023-04-25T17:59:47Z)
• URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation [24.03121823263355]
  We introduce an uncertainty rectified cross-distillation between Transformer and convolutional neural network (CNN) to learn a unified depth estimator. Specifically, we use the depth estimates from the Transformer branch and the CNN branch as pseudo labels to teach each other. We propose a surprisingly simple yet highly effective data augmentation technique CutFlip, which enforces the model to exploit more valuable clues apart from the vertical image position for depth inference.
  arXiv  Detail & Related papers  (2023-02-16T08:53:08Z)
• Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion [6.491470878214977]
  This paper benchmarks various transformer-based models for the depth estimation task on an indoor NYUV2 dataset and an outdoor KITTI dataset. We propose a novel attention-based architecture, Depthformer for monocular depth estimation. Our proposed method improves the state-of-the-art by 3.3%, and 3.3% respectively in terms of Root Mean Squared Error (RMSE)
  arXiv  Detail & Related papers  (2022-07-10T20:49:11Z)
• 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)
• Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction [91.43066633305662]
  We propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD) Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time.
  arXiv  Detail & Related papers  (2022-03-09T17:20:18Z)
• Depth Completion using Plane-Residual Representation [84.63079529738924]
  We introduce a novel way of interpreting depth information with the closest depth plane label $p$ and a residual value $r$, as we call it, Plane-Residual (PR) representation. By interpreting depth information in PR representation and using our corresponding depth completion network, we were able to acquire improved depth completion performance with faster computation.
  arXiv  Detail & Related papers  (2021-04-15T10:17:53Z)
• Discrete Cosine Transform Network for Guided Depth Map Super-Resolution [19.86463937632802]
  The goal is to use high-resolution (HR) RGB images to provide extra information on edges and object contours, so that low-resolution depth maps can be upsampled to HR ones. We propose an advanced Discrete Cosine Transform Network (DCTNet), which is composed of four components. We show that our method can generate accurate and HR depth maps, surpassing state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-14T17:01:03Z)
• Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion [56.85837052421469]
  Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from a single RGB image with optional sparse measurements from low-cost active depth sensors. We introduce Sparse Networks (SANs), a new module enabling monodepth networks to perform both the tasks of depth prediction and completion.
  arXiv  Detail & Related papers  (2021-03-30T21:22:26Z)
• A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection [89.88222217065858]
  We design a single stream network to use the depth map to guide early fusion and middle fusion between RGB and depth. This model is 55.5% lighter than the current lightest model and runs at a real-time speed of 32 FPS when processing a $384 times 384$ image.
  arXiv  Detail & Related papers  (2020-07-14T04:40:14Z)

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.