Research map / Image generation / Text-to-image diffusion
Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer
Fuxiang Wu, Liu Liu, Fusheng Hao, Fengxiang He, Jun Cheng
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add detail enhancement to the joint-decoding transformer (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | IS: 30.09 ± 0.32 -> 34.58 ± 0.39 | Improved |
| add detail enhancement to the joint-decoding transformer (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | FID: 10.50 -> 12.26 | Hurt |
| add detail enhancement to the joint-decoding transformer (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | R-precision (CLIP): 64.02 ± 0.92 -> 70.27 ± 0.53 | Improved |
| jointly decode image and layout tokens instead of not jointly decoding (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | IS: decrease 0.73 | Improved |
| jointly decode image and layout tokens instead of not jointly decoding (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | FID: increase 0.87 | Improved |
| jointly decode image and layout tokens instead of not jointly decoding (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | R-precision (CLIP): decrease 2.17% | Improved |
| allow joint decoding rather than constrain decoding to a predefined layout (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | IS: 33.48 ± 0.41 -> 34.58 ± 0.39 | Improved |
| allow joint decoding rather than constrain decoding to a predefined layout (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | FID: 12.27 -> 12.26 | No clear effect |
| allow joint decoding rather than constrain decoding to a predefined layout (ablation) | Object-Guided Joint-Decoding Transformer · MS-COCO | R-precision (CLIP): 68.83 ± 0.89 -> 70.27 ± 0.53 | Improved |
| use the proposed full method instead of DM-GAN* | MS-COCO text-to-image synthesis · MS-COCO | IS: 34.05 ± 0.49 -> 34.58 ± 0.39 | Improved |
| use the proposed full method instead of OPGAN* | MS-COCO text-to-image synthesis · MS-COCO | FID: 22.04 -> 12.26 | Improved |
| use the proposed full method instead of DM-GAN* | MS-COCO text-to-image synthesis · MS-COCO | R-precision (CLIP): 66.01 ± 0.85 -> 70.27 ± 0.53 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CogView — CogView: Mastering Text-to-Image Generation via Transformers (NeurIPS 2021) · better on 2 of 2 shared results
- DM-GAN* — DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (CVPR 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (CVPR 2024 · similarity 0.87)
- DreamText: High Fidelity Scene Text Synthesis (CVPR 2025 · similarity 0.86)
- Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis (CVPR 2024 · similarity 0.86)
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts (ICLR 2024 · similarity 0.86)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.86)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
