Rethinking RAFT for Efficient Optical Flow

• URL: http://arxiv.org/abs/2401.00833v1
• Date: Mon, 1 Jan 2024 18:23:39 GMT
• Title: Rethinking RAFT for Efficient Optical Flow
• Authors: Navid Eslami, Farnoosh Arefi, Amir M. Mansourian, Shohreh Kasaei
• Abstract summary: This paper proposes a novel approach based on the RAFT framework. It incorporates the attention mechanism to handle global feature extraction and address repetitive patterns. The proposed method, Efficient RAFT (Ef-RAFT),achieves significant improvements of 10% on the Sintel dataset and 5% on the KITTI dataset over RAFT.
• Score: 9.115508086522887
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these algorithms contribute to this issue. Additionally, some existing methods suffer from slow runtime and excessive graphic memory consumption. To address these problems, this paper proposes a novel approach based on the RAFT framework. The proposed Attention-based Feature Localization (AFL) approach incorporates the attention mechanism to handle global feature extraction and address repetitive patterns. It introduces an operator for matching pixels with corresponding counterparts in the second frame and assigning accurate flow values. Furthermore, an Amorphous Lookup Operator (ALO) is proposed to enhance convergence speed and improve RAFTs ability to handle large displacements by reducing data redundancy in its search operator and expanding the search space for similarity extraction. The proposed method, Efficient RAFT (Ef-RAFT),achieves significant improvements of 10% on the Sintel dataset and 5% on the KITTI dataset over RAFT. Remarkably, these enhancements are attained with a modest 33% reduction in speed and a mere 13% increase in memory usage. The code is available at: https://github.com/n3slami/Ef-RAFT

Related papers

• Accelerating spherical K-means clustering for large-scale sparse document data [0.7366405857677226]
  This paper presents an accelerated spherical K-means clustering algorithm for large-scale and high-dimensional sparse document data sets. We experimentally demonstrate that our algorithm efficiently achieves superior speed performance in large-scale documents compared with algorithms using the state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-11-18T05:50:58Z)
• EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration [1.741980945827445]
  We propose EfficientMorph, a transformer-based architecture for unsupervised 3D image registration. It optimize the balance between local and global attention through a plane-based attention mechanism. It reduces computational redundancy via cascaded group attention, and captures fine details without compromising computational efficiency.
  arXiv  Detail & Related papers  (2024-03-16T22:01:55Z)
• Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed [42.861344584752]
  Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios. We revisit its design choices and derive multiple improvements for both efficiency and accuracy. Our method can achieve higher accuracy compared with competitive semi-dense matchers.
  arXiv  Detail & Related papers  (2024-03-07T18:58:40Z)
• SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector [60.42293239557962]
  We propose SpirDet, a novel approach for efficient detection of infrared small targets. We employ a new dual-branch sparse decoder to restore the feature map. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2024-02-08T05:06:14Z)
• MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Table [62.164549651134465]
  We propose MF-NeRF, a memory-efficient NeRF framework that employs a Mixed-Feature hash table to improve memory efficiency and reduce training time while maintaining reconstruction quality. Our experiments with state-of-the-art Instant-NGP, TensoRF, and DVGO, indicate our MF-NeRF could achieve the fastest training time on the same GPU hardware with similar or even higher reconstruction quality.
  arXiv  Detail & Related papers  (2023-04-25T05:44:50Z)
• Gradient Backpropagation based Feature Attribution to Enable Explainable-AI on the Edge [1.7338677787507768]
  In this work, we analyze the dataflow of gradient backpropagation based feature attribution algorithms to determine the resource overhead required over inference. We develop a High-Level Synthesis (HLS) based FPGA design that is targeted for edge devices and supports three feature attribution algorithms. Our design methodology demonstrates a pathway to repurpose inference accelerators to support feature attribution with minimal overhead, thereby enabling real-time XAI on the edge.
  arXiv  Detail & Related papers  (2022-10-19T22:58:59Z)
• Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search [96.20505710087392]
  We propose a Shapley value based method to evaluate operation contribution (Shapley-NAS) for neural architecture search. We show that our method outperforms the state-of-the-art methods by a considerable margin with light search cost.
  arXiv  Detail & Related papers  (2022-06-20T14:41:49Z)
• Attention-based Proposals Refinement for 3D Object Detection [0.0]
  This paper takes a more data-driven approach to ROI feature extraction using the attention mechanism. Experiments on KITTI textitvalidation set show that our method achieves competitive performance of 84.84 AP for class Car at moderate difficulty.
  arXiv  Detail & Related papers  (2022-01-18T15:50:31Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• RAFT: Recurrent All-Pairs Field Transforms for Optical Flow [78.92562539905951]
  We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field. RAFT achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-26T17:12:42Z)
• Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution [82.1739023587565]
  We propose a novel spectral-spatial residual network for hyperspectral image super-resolution (SSRNet) Our method can effectively explore spatial-spectral information by using 3D convolution instead of 2D convolution, which enables the network to better extract potential information. In each unit, we employ spatial and temporal separable 3D convolution to extract spatial and spectral information, which not only reduces unaffordable memory usage and high computational cost, but also makes the network easier to train.
  arXiv  Detail & Related papers  (2020-01-14T03:34:55Z)

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.