mlsanityData to 14 Oct 2026

Learning Object Placement via Dual-path Graph Completion

arXiv 2207.11464 ↗First posted 23 Jul 2022cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Object placement aims to place a foreground object over a background image with a suitable location and size. In this work, we treat object placement as a graph completion problem and propose a novel graph completion module (GCM). The background scene is represented by a graph with multiple nodes at different spatial locations with various receptive fields. The foreground object is encoded as a special node that should be inserted at a reasonable place in this graph. We also design a dual-path framework upon the structure of GCM to fully exploit annotated composite images. With extensive experiments on OPA dataset, our method proves to significantly outperform existing methods in generating plausible object placement without loss of diversity.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 23 Jul 2022.

Builds on

29 of 44 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  7. 2015Spatial Transformer Networkscited by 1,429
  8. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  9. 2018Self-Attention with Relative Position Representationscited by 1,120
  10. 2017Convolutional Sequence to Sequence Learningcited by 552
  11. 2018Image Generation from Scene Graphscited by 324
  12. 2019DoveNet: Deep Image Harmonization via Domain Verificationcited by 135
17 more
  1. 2017Deep Image Harmonizationcited by 120
  2. 2018ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositingcited by 90
  3. 2019Putting Humans in a Scene: Learning Affordance in 3D Indoor Environmentscited by 72
  4. 2017GP-GAN: Towards Realistic High-Resolution Image Blendingcited by 64
  5. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  6. 2019Deep Image Blendingcited by 62
  7. 2020Learning to Encode Position for Transformer with Continuous Dynamical Modelcited by 61
  8. 2021High-Resolution Image Harmonization via Collaborative Dual Transformationscited by 55
  9. 2015Learning a Discriminative Model for the Perception of Realism in Composite Imagescited by 52
  10. 2019Learning to Generate Synthetic Data via Compositingcited by 52
  11. 2020BargainNet: Background-Guided Domain Translation for Image Harmonizationcited by 52
  12. 2017Synthesizing Training Data for Object Detection in Indoor Scenescited by 48
  13. 2018Context-Aware Synthesis and Placement of Object Instancescited by 41
  14. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  15. 2021OPA: Object Placement Assessment Datasetcited by 28
  16. 2017Where and Who? Automatic Semantic-Aware Person Compositioncited by 21
  17. 2018What and Where: A Context-based Recommendation System for Object Insertioncited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 6; 2026: 4.

20 papers.

Sort:

By area:

  1. 2023Iterative Multi-granular Image Editing using Diffusion Modelscited by 20
  2. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
  3. 2023SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Controlcited by 18
  4. 2023DreamCom: Finetuning Text-guided Inpainting Model for Image Compositioncited by 17
  5. 2024Text2Place: Affordance-aware Text Guided Human Placementcited by 11
  6. 2023Scene-aware Human Pose Generation using Transformercited by 9
  7. 2023Foreground Object Search by Distilling Composite Image Featurecited by 6
  8. 2024Imagining the Unseen: Generative Location Modeling for Object Placementcited by 4
  9. 2024DiffPop: Plausibility-Guided Object Placement Diffusion for Image Compositioncited by 3
  10. 2025BOOTPLACE: Bootstrapped Object Placement with Detection Transformerscited by 3
  11. 2025Object Placement for Anythingcited by 3
  12. 2025AnimateScene: Camera-controllable Animation in Any Scenecited by 3
8 more
  1. 2024Rethinking Referring Object Removalcited by 0
  2. 2025Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generationcited by 0
  3. 2025GraPLUS: Graph-based Placement Using Semantics for Image Compositioncited by 0
  4. 2025Beyond Realism: Learning the Art of Expressive Composition with StickerNetcited by 0
  5. 2026HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object Placementcited by 0
  6. 2026Learning to Understand Body Language from Flight through Robust 3D Avatar Placingcited by 0
  7. 2026presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Searchcited by 0
  8. 2026Hybrid Generative-Discriminative Object Placementcited by 0