Xinglong Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinglong Wu has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Pengze Zhang
Bytedance, Beijing, China
2 shared publications - Qian He
Bytedance, Beijing, China
2 shared publications - Songtao Zhao
Bytedance, Beijing, China
2 shared publications - Xinghui Li
Bytedance, Beijing, China
2 shared publications - Bin Xia
ByteDance Inc., Beijing, China
1 shared publication - Chong Mou
School of Electronic and Computer Engineering, Peking University, Shenzhen, China
1 shared publication
Latest Publications
- 7 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (8) , 9502-9518
DreamFuse: Toward Realistic and Seamless Image Fusion Across Diverse Scenarios
Image fusion seeks to seamlessly integrate fore ground objects with background scenes, producing realistic and harmonious fused images. While existing methods often insert objects directly, adaptive and interactive fusion—requiring contextual adaptation and foreground-background interplay—remains a challenging yet critical task. To address this, we first propose a pipeline for generating high-quality fusion data. By combining iterative in-context learning with existing tools, we curate a diverse cross-scene dataset supporting three core tasks: object integration, replacement, and attribute-referenced editing. Lever aging this, we introduce DreamFuse, a unified diffusion-based approach that jointly optimizes these capabilities. DreamFuse exploits the Diffusion Transformer (DiT) architecture, using its attention mechanism to extract and align foreground-background features for coherent fusion. For flexible control, we incorporate a Positional Affine mechanism, enabling precise spatial and scale adjustments while supporting diverse text-driven fusion. Fur thermore, we employ Localized Direct Preference Optimization (L-DPO), refining the model via human feedback to enhance harmony and consistency. Extensive experimental results demon strate DreamFuse's superiority over state-of-the-art approaches across multiple metrics.
- 7 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (8) , 9502-9518
DreamFuse: Toward Realistic and Seamless Image Fusion Across Diverse Scenarios
Image fusion seeks to seamlessly integrate fore ground objects with background scenes, producing realistic and harmonious fused images. While existing methods often insert objects directly, adaptive and interactive fusion—requiring contextual adaptation and foreground-background interplay—remains a challenging yet critical task. To address this, we first propose a pipeline for generating high-quality fusion data. By combining iterative in-context learning with existing tools, we curate a diverse cross-scene dataset supporting three core tasks: object integration, replacement, and attribute-referenced editing. Lever aging this, we introduce DreamFuse, a unified diffusion-based approach that jointly optimizes these capabilities. DreamFuse exploits the Diffusion Transformer (DiT) architecture, using its attention mechanism to extract and align foreground-background features for coherent fusion. For flexible control, we incorporate a Positional Affine mechanism, enabling precise spatial and scale adjustments while supporting diverse text-driven fusion. Fur thermore, we employ Localized Direct Preference Optimization (L-DPO), refining the model via human feedback to enhance harmony and consistency. Extensive experimental results demon strate DreamFuse's superiority over state-of-the-art approaches across multiple metrics.
- Top Cited PapersOpen Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
DreamO: A Unified Framework for Image Customization
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Top Cited PapersOpen AccessDreamO: A Unified Framework for Image Customization
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessDreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (3) , 1578-1593
DiffI2I: Efficient Diffusion Model for Image-to-Image Translation
The Diffusion Model (DM) has emerged as the SOTA approach for image synthesis. However, the existing DM cannot perform well on some image-to-image translation (I2I) tasks. Different from image synthesis, some I2I tasks, such as super-resolution, require generating results in accordance with GT images. Traditional DMs for image synthesis require extensive iterations and large denoising models to estimate entire images, which gives their strong generative ability but also leads to artifacts and inefficiency for I2I. To tackle this challenge, we propose a simple, efficient, and powerful DM framework for I2I, called DiffI2I. Specifically, DiffI2I comprises three key components: a compact I2I prior extraction network (CPEN), a dynamic I2I transformer (DI2Iformer), and a denoising network. We train DiffI2I in two stages: pretraining and DM training. For pretraining, GT and input images are fed into CPEN $_{S1}$ to capture a compact I2I prior representation (IPR) guiding DI2Iformer. In the second stage, the DM is trained to only use the input images to estimate the same IRP as CPEN $_{S1}$ . Compared to traditional DMs, the compact IPR enables DiffI2I to obtain more accurate outcomes and employ a lighter denoising network and fewer iterations. Through extensive experiments on various I2I tasks, we demonstrate that DiffI2I achieves SOTA performance while significantly reducing computational burdens.
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (3) , 1578-1593
DiffI2I: Efficient Diffusion Model for Image-to-Image Translation
The Diffusion Model (DM) has emerged as the SOTA approach for image synthesis. However, the existing DM cannot perform well on some image-to-image translation (I2I) tasks. Different from image synthesis, some I2I tasks, such as super-resolution, require generating results in accordance with GT images. Traditional DMs for image synthesis require extensive iterations and large denoising models to estimate entire images, which gives their strong generative ability but also leads to artifacts and inefficiency for I2I. To tackle this challenge, we propose a simple, efficient, and powerful DM framework for I2I, called DiffI2I. Specifically, DiffI2I comprises three key components: a compact I2I prior extraction network (CPEN), a dynamic I2I transformer (DI2Iformer), and a denoising network. We train DiffI2I in two stages: pretraining and DM training. For pretraining, GT and input images are fed into CPEN $_{S1}$ to capture a compact I2I prior representation (IPR) guiding DI2Iformer. In the second stage, the DM is trained to only use the input images to estimate the same IRP as CPEN $_{S1}$ . Compared to traditional DMs, the compact IPR enables DiffI2I to obtain more accurate outcomes and employ a lighter denoising network and fewer iterations. Through extensive experiments on various I2I tasks, we demonstrate that DiffI2I achieves SOTA performance while significantly reducing computational burdens.