mlsanityData to 7 Oct 2026

Fast Object Placement Assessment

arXiv 2205.14280 ↗First posted 28 May 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Object placement assessment (OPA) aims to predict the rationality score of a composite image in terms of the placement (e.g., scale, location) of inserted foreground object. However, given a pair of scaled foreground and background, to enumerate all the reasonable locations, existing OPA model needs to place the foreground at each location on the background and pass the obtained composite image through the model one at a time, which is very time-consuming. In this work, we investigate a new task named as fast OPA. Specifically, provided with a scaled foreground and a background, we only pass them through the model once and predict the rationality scores for all locations. To accomplish this task, we propose a pioneering fast OPA model with several innovations (i.e., foreground dynamic filter, background prior transfer, and composite feature mimicking) to bridge the performance gap between slow OPA model and fast OPA model. Extensive experiments on OPA dataset show that our proposed fast OPA model performs on par with slow OPA model but runs significantly faster.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 40 of its 53 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

40 of 53 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  5. 2020Knowledge Distillation: A Surveycited by 1,578
  6. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  7. 2020Conditional Convolutions for Instance Segmentationcited by 314
  8. 2019Structured Knowledge Distillation for Dense Predictioncited by 277
  9. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  10. 2018Paraphrasing Complex Network: Network Compression via Factor Transfercited by 255
  11. 2018Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neuronscited by 235
  12. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
28 more
  1. 2020Channel-wise Knowledge Distillation for Dense Predictioncited by 161
  2. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 134
  3. 2019Pixel-Adaptive Convolutional Neural Networkscited by 126
  4. 2017Deep Image Harmonizationcited by 120
  5. 2019CARAFE: Content-Aware ReAssembly of FEaturescited by 119
  6. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  7. 2018Modeling Visual Context is Key to Augmenting Object Detection Datasetscited by 106
  8. 2019InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pastingcited by 95
  9. 2021GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Drivingcited by 75
  10. 2019Improving the Harmony of the Composite Image by Spatial-Separated Attention Modulecited by 73
  11. 2020Heterogeneous Knowledge Distillation using Information Flow Modelingcited by 73
  12. 2020Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detectioncited by 72
  13. 2021Region-aware Adaptive Instance Normalization for Image Harmonizationcited by 71
  14. 2018Fast Human Pose Estimationcited by 68
  15. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  16. 2020Foreground-aware Semantic Representations for Image Harmonizationcited by 53
  17. 2019Learning to Generate Synthetic Data via Compositingcited by 52
  18. 2021Decoupled Dynamic Filter Networkscited by 52
  19. 2017Synthesizing Training Data for Object Detection in Indoor Scenescited by 48
  20. 2018Learning to Segment via Cut-and-Pastecited by 42
  21. 2018Context-Aware Synthesis and Placement of Object Instancescited by 41
  22. 2019Depthwise Convolution is All You Need for Learning Multiple Visual Domainscited by 36
  23. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  24. 2021OPA: Object Placement Assessment Datasetcited by 28
  25. 2017Where and Who? Automatic Semantic-Aware Person Compositioncited by 21
  26. 2017Classification Driven Dynamic Image Enhancementcited by 15
  27. 2018What and Where: A Context-based Recommendation System for Object Insertioncited by 14
  28. 2019Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 4; 2026: 3.

12 papers.

  1. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
  2. 2023SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Controlcited by 18
  3. 2023Foreground Object Search by Distilling Composite Image Featurecited by 6
  4. 2024Imagining the Unseen: Generative Location Modeling for Object Placementcited by 4
  5. 2025BOOTPLACE: Bootstrapped Object Placement with Detection Transformerscited by 3
  6. 2025Object Placement for Anythingcited by 3
  7. 2024Deep Image Composition Meets Image Forgerycited by 2
  8. 2025CAD2DMD-SET: Synthetic Generation Tool of Digital Measurement Device CAD Model Datasets for fine-tuning Large Vision-Language Modelscited by 1
  9. 2025Beyond Realism: Learning the Art of Expressive Composition with StickerNetcited by 0
  10. 2026VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusioncited by 0
  11. 2026HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object Placementcited by 0
  12. 2026Hybrid Generative-Discriminative Object Placementcited by 0