mlsanityData to 7 Oct 2026

Technique Report of CVPR 2024 PBDL Challenges

arXiv 2406.10744 ↗First posted 15 Jun 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 71 of its 130 references that are in the map. First posted on arXiv 15 Jun 2024.

Builds on

71 of 130 references.

References · 71

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  9. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  10. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  11. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  12. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
38 more
  1. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  2. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  3. 2021Multi-Stage Progressive Image Restorationcited by 813
  4. 2022Simple Baselines for Image Restorationcited by 701
  5. 2017Video Enhancement with Task-Oriented Flowcited by 612
  6. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  7. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  8. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  9. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  10. 2018Learning to See in the Darkcited by 459
  11. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  12. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  13. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  14. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  15. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  16. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  17. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  18. 2019Events-to-Video: Bringing Modern Computer Vision to Event Camerascited by 191
  19. 2022Focal Modulation Networkscited by 186
  20. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182
  21. 2018A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimationcited by 178
  22. 2020Human-Aware Motion Deblurringcited by 174
  23. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  24. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  25. 2021Instances as Queriescited by 157
  26. 2017Burst Denoising with Kernel Prediction Networkscited by 156
  27. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  28. 2020A Physics-based Noise Formation Model for Extreme Low-light Raw Denoisingcited by 138
  29. 2019FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimationcited by 128
  30. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
  31. 2021Event-Based Fusion for Motion Deblurring with Cross-modal Attentioncited by 112
  32. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  33. 2023Global Structure-Aware Diffusion Process for Low-Light Image Enhancementcited by 92
  34. 2018DeepISP: Towards Learning an End-to-End Image Processing Pipelinecited by 88
  35. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  36. 2021Object Tracking by Jointly Exploiting Frame and Event Domaincited by 83
  37. 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
  38. 2020Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenescited by 77

50 most cited of 71 All 71 (JSON)

Built on by

Not cited yet.