mlsanityData to 14 Oct 2026

UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block

arXiv 2507.19948 ↗First posted 26 Jul 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Depth estimation plays a crucial role in 3D scene understanding and is extensively used in a wide range of vision tasks. Image-based methods struggle in challenging scenarios, while event cameras offer high dynamic range and temporal resolution but face difficulties with sparse data. Combining event and image data provides significant advantages, yet effective integration remains challenging. Existing CNN-based fusion methods struggle with occlusions and depth disparities due to limited receptive fields, while Transformer-based fusion methods often lack deep modality interaction. To address these issues, we propose UniCT Depth, an event-image fusion method that unifies CNNs and Transformers to model local and global features. We propose the Convolution-compensated ViT Dual SA (CcViT-DA) Block, designed for the encoder, which integrates Context Modeling Self-Attention (CMSA) to capture spatial dependencies and Modal Fusion Self-Attention (MFSA) for effective cross-modal fusion. Furthermore, we design the tailored Detail Compensation Convolution (DCC) Block to improve texture details and enhances edge representations. Experiments show that UniCT Depth outperforms existing image, event, and fusion-based monocular depth estimation methods across key metrics.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 26 Jul 2025.

Builds on

26 of 41 references.

References · 26

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021Vision Transformers for Dense Predictioncited by 1,803
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  7. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  8. 2018Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotioncited by 307
  9. 2018The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perceptioncited by 254
  10. 2016Single-Image Depth Perception in the Wildcited by 180
  11. 2018A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimationcited by 178
  12. 2022DaViT: Dual Attention Vision Transformerscited by 175
14 more
  1. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  2. 2021Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Predictioncited by 90
  3. 2020Learning Monocular Dense Depth from Eventscited by 85
  4. 2023IEBins: Iterative Elastic Bins for Monocular Depth Estimationcited by 54
  5. 2022Event Transformer. A sparse-aware solution for efficient event data processingcited by 50
  6. 2023Hierarchical Neural Memory Network for Low Latency Event Processingcited by 47
  7. 2021Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translationcited by 32
  8. 2020Perception and Navigation in Autonomous Systems in the Era of Learning: A Surveycited by 30
  9. 2019Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and Morecited by 29
  10. 2021Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervisioncited by 24
  11. 2023EVEN: An Event-Based Framework for Monocular Depth Estimation at Adverse Night Conditionscited by 19
  12. 2022Event Transformer+. A multi-purpose solution for efficient event data processingcited by 13
  13. 2023SRFNet: Monocular Depth Estimation with Fine-grained Structure via Spatial Reliability-oriented Fusion of Frames and Eventscited by 13
  14. 2024GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Predictioncited by 0
  2. 2026Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimationcited by 0
  3. 2026UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generationcited by 0