SRFNet: Monocular Depth Estimation with Fine-grained Structure via Spatial Reliability-oriented Fusion of Frames and Events

• URL: http://arxiv.org/abs/2309.12842v2
• Date: Wed, 24 Jul 2024 13:38:33 GMT
• Title: SRFNet: Monocular Depth Estimation with Fine-grained Structure via Spatial Reliability-oriented Fusion of Frames and Events
• Authors: Tianbo Pan, Zidong Cao, Lin Wang,
• Abstract summary: Traditional frame-based methods suffer from performance drops due to limited dynamic range and motion blur. Recent works leverage novel event cameras to complement or guide the frame modality via frame-event feature fusion. SRFNet can estimate depth with fine-grained structure at both daytime and nighttime.
• Score: 5.800516204046145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular depth estimation is a crucial task to measure distance relative to a camera, which is important for applications, such as robot navigation and self-driving. Traditional frame-based methods suffer from performance drops due to the limited dynamic range and motion blur. Therefore, recent works leverage novel event cameras to complement or guide the frame modality via frame-event feature fusion. However, event streams exhibit spatial sparsity, leaving some areas unperceived, especially in regions with marginal light changes. Therefore, direct fusion methods, e.g., RAMNet, often ignore the contribution of the most confident regions of each modality. This leads to structural ambiguity in the modality fusion process, thus degrading the depth estimation performance. In this paper, we propose a novel Spatial Reliability-oriented Fusion Network (SRFNet), that can estimate depth with fine-grained structure at both daytime and nighttime. Our method consists of two key technical components. Firstly, we propose an attention-based interactive fusion (AIF) module that applies spatial priors of events and frames as the initial masks and learns the consensus regions to guide the inter-modal feature fusion. The fused feature are then fed back to enhance the frame and event feature learning. Meanwhile, it utilizes an output head to generate a fused mask, which is iteratively updated for learning consensual spatial priors. Secondly, we propose the Reliability-oriented Depth Refinement (RDR) module to estimate dense depth with the fine-grained structure based on the fused features and masks. We evaluate the effectiveness of our method on the synthetic and real-world datasets, which shows that, even without pretraining, our method outperforms the prior methods, e.g., RAMNet, especially in night scenes. Our project homepage: https://vlislab22.github.io/SRFNet.

Related papers

• Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection [17.406051477690134]
  Event cameras output sparse and asynchronous events, providing a potential solution to solve these problems. We propose a novel hierarchical feature refinement network for event-frame fusion. Our method exhibits significantly better robustness when introducing 15 different corruption types to the frame images.
  arXiv  Detail & Related papers  (2024-07-17T14:09:46Z)
• Fusion-Mamba for Cross-modality Object Detection [63.56296480951342]
  Cross-modality fusing information from different modalities effectively improves object detection performance. We design a Fusion-Mamba block (FMB) to map cross-modal features into a hidden state space for interaction. Our proposed approach outperforms the state-of-the-art methods on $m$AP with 5.9% on $M3FD$ and 4.9% on FLIR-Aligned datasets.
  arXiv  Detail & Related papers  (2024-04-14T05:28:46Z)
• Embracing Compact and Robust Architectures for Multi-Exposure Image Fusion [50.598654017728045]
  We propose a search-based paradigm, involving self-alignment and detail repletion modules for robust multi-exposure image fusion. By utilizing scene relighting and deformable convolutions, the self-alignment module can accurately align images despite camera movement. We realize the state-of-the-art performance in comparison to various competitive schemes, yielding a 4.02% and 29.34% improvement in PSNR for general and misaligned scenarios.
  arXiv  Detail & Related papers  (2023-05-20T17:01:52Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Video Semantic Segmentation with Inter-Frame Feature Fusion and Inner-Frame Feature Refinement [39.06589186472675]
  We propose a spatial-temporal fusion (STF) module to model dense pairwise relationships among multi-frame features. Besides, we propose a novel memory-augmented refinement (MAR) module to tackle difficult predictions among semantic boundaries.
  arXiv  Detail & Related papers  (2023-01-10T07:57:05Z)
• RGB-Event Fusion for Moving Object Detection in Autonomous Driving [3.5397758597664306]
  Moving Object Detection (MOD) is a critical vision task for successfully achieving safe autonomous driving. Recent advances in sensor technologies, especially the Event camera, can naturally complement the conventional camera approach to better model moving objects. We propose RENet, a novel RGB-Event fusion Network, that jointly exploits the two complementary modalities to achieve more robust MOD.
  arXiv  Detail & Related papers  (2022-09-17T12:59:08Z)
• NeuralFusion: Online Depth Fusion in Latent Space [77.59420353185355]
  We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. Our approach is real-time capable, handles high noise levels, and is particularly able to deal with gross outliers common for photometric stereo-based depth maps.
  arXiv  Detail & Related papers  (2020-11-30T13:50:59Z)
• Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos [48.57686258913474]
  Video action recognition has been partially addressed by the CNNs stacking of fixed-size 3D kernels. We propose to learn the optimal-scale kernels from the data. An textitaction perceptron synthesizer is proposed to generate the kernels from a bag of fixed-size kernels.
  arXiv  Detail & Related papers  (2020-07-22T14:22:29Z)
• 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)
• RoutedFusion: Learning Real-time Depth Map Fusion [73.0378509030908]
  We present a novel real-time capable machine learning-based method for depth map fusion. We propose a neural network that predicts non-linear updates to better account for typical fusion errors. Our network is composed of a 2D depth routing network and a 3D depth fusion network which efficiently handle sensor-specific noise and outliers.
  arXiv  Detail & Related papers  (2020-01-13T16:46:41Z)

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.