SFMNet: Sparse Focal Modulation for 3D Object Detection

• URL: http://arxiv.org/abs/2503.12093v1
• Date: Sat, 15 Mar 2025 11:40:58 GMT
• Title: SFMNet: Sparse Focal Modulation for 3D Object Detection
• Authors: Oren Shrout, Ayellet Tal,
• Abstract summary: SFMNet is a novel 3D sparse detector that combines the efficiency of sparse convolutions with the ability to model long-range dependencies.<n>We show that our detector achieves state-of-the-art performance on autonomous driving datasets.
• Score: 11.19540223578237
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose SFMNet, a novel 3D sparse detector that combines the efficiency of sparse convolutions with the ability to model long-range dependencies. While traditional sparse convolution techniques efficiently capture local structures, they struggle with modeling long-range relationships. However, capturing long-range dependencies is fundamental for 3D object detection. In contrast, transformers are designed to capture these long-range dependencies through attention mechanisms. But, they come with high computational costs, due to their quadratic query-key-value interactions. Furthermore, directly applying attention to non-empty voxels is inefficient due to the sparse nature of 3D scenes. Our SFMNet is built on a novel Sparse Focal Modulation (SFM) module, which integrates short- and long-range contexts with linear complexity by leveraging a new hierarchical sparse convolution design. This approach enables SFMNet to achieve high detection performance with improved efficiency, making it well-suited for large-scale LiDAR scenes. We show that our detector achieves state-of-the-art performance on autonomous driving datasets.

Related papers

• DFIR-DETR: Frequency Domain Enhancement and Dynamic Feature Aggregation for Cross-Scene Small Object Detection [16.16000521213211]
  Small object detection in UAV remote sensing images is difficult.<n>Current transformer-based detectors struggle with three critical issues.<n>We introduce DFIR-DETR to tackle these problems through dynamic feature aggregation combined with frequency-domain processing.
  arXiv  Detail & Related papers  (2025-12-08T01:25:10Z)
• FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices [38.61635285386612]
  Existing LiDAR 3D object detection methods rely on sparse convolutions and/or transformers, which can be challenging to run on resource-constrained edge devices.<n>We propose FALO, a hardware-friendly approach to LiDAR 3D detection, which offers both state-of-the-art (SOTA) detection accuracy and fast inference speed.
  arXiv  Detail & Related papers  (2025-06-04T22:46:28Z)
• DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking [50.038098341549095]
  State estimation is challenging for 3D object tracking with high maneuverability.<n>We propose a novel framework, DIMM, to effectively combine estimates from different motion models in each direction.<n>DIMM significantly improves the tracking accuracy of existing state estimation methods by 31.61%99.23%.
  arXiv  Detail & Related papers  (2025-05-18T10:12:41Z)
• State Space Model Meets Transformer: A New Paradigm for 3D Object Detection [33.49952392298874]
  We propose a new 3D object DEtection paradigm with an interactive STate space model (DEST) In the interactive SSM, we design a novel state-dependent SSM parameterization method that enables system states to effectively serve as queries in 3D indoor detection tasks. Our method improves the GroupFree baseline in terms of AP50 on ScanNet V2 and SUN RGB-D datasets.
  arXiv  Detail & Related papers  (2025-03-18T17:58:03Z)
• Efficient Oriented Object Detection with Enhanced Small Object Recognition in Aerial Images [2.9138705529771123]
  We present a novel enhancement to the YOLOv8 model, tailored for oriented object detection tasks.<n>Our model features a wavelet transform-based C2f module for capturing associative features and an Adaptive Scale Feature Pyramid (ASFP) module that leverages P2 layer details.<n>Our approach provides a more efficient architectural design than DecoupleNet, which has 23.3M parameters, all while maintaining detection accuracy.
  arXiv  Detail & Related papers  (2024-12-17T05:45:48Z)
• Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving [69.20604395205248]
  We present a new 3D point-based detector model, named Shift-SSD, for precise 3D object detection in autonomous driving. We introduce an intriguing Cross-Cluster Shifting operation to unleash the representation capacity of the point-based detector. We conduct extensive experiments on the KITTI, runtime, and nuScenes datasets, and the results demonstrate the state-of-the-art performance of Shift-SSD.
  arXiv  Detail & Related papers  (2024-03-10T10:36:32Z)
• Large receptive field strategy and important feature extraction strategy in 3D object detection [6.3948571459793975]
  This study focuses on key challenges in 3D target detection. To tackle the challenge of expanding the receptive field of a 3D convolutional kernel, we introduce the Dynamic Feature Fusion Module. This module achieves adaptive expansion of the 3D convolutional kernel's receptive field, balancing the expansion with acceptable computational loads.
  arXiv  Detail & Related papers  (2024-01-22T13:01:28Z)
• PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection [66.94819989912823]
  We propose a point-trajectory transformer with long short-term memory for efficient temporal 3D object detection. We use point clouds of current-frame objects and their historical trajectories as input to minimize the memory bank storage requirement. We conduct extensive experiments on the large-scale dataset to demonstrate that our approach performs well against state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-13T18:59:13Z)
• UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation [93.88170217725805]
  We propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features. Our evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-12-08T18:59:57Z)
• Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes [82.4186966781934]
  We introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules. With negligible extra overhead, Ret3D achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-18T03:48:58Z)
• Focal Sparse Convolutional Networks for 3D Object Detection [121.45950754511021]
  We introduce two new modules to enhance the capability of Sparse CNNs. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolution with fusion. For the first time, we show that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection.
  arXiv  Detail & Related papers  (2022-04-26T17:34:10Z)
• LocATe: End-to-end Localization of Actions in 3D with Transformers [91.28982770522329]
  LocATe is an end-to-end approach that jointly localizes and recognizes actions in a 3D sequence. Unlike transformer-based object-detection and classification models which consider image or patch features as input, LocATe's transformer model is capable of capturing long-term correlations between actions in a sequence. We introduce a new, challenging, and more realistic benchmark dataset, BABEL-TAL-20 (BT20), where the performance of state-of-the-art methods is significantly worse.
  arXiv  Detail & Related papers  (2022-03-21T03:35:32Z)
• Voxel Transformer for 3D Object Detection [133.34678177431914]
  Voxel Transformer (VoTr) is a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Our proposed VoTr shows consistent improvement over the convolutional baselines while maintaining computational efficiency on the KITTI dataset and the Open dataset.
  arXiv  Detail & Related papers  (2021-09-06T14:10:22Z)

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.