Zheng Gu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zheng Gu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Yang Gao
Nanjing University
5 shared publications - Jing Huo
Nanjing University
4 shared publications - Jing Liao
City University of Hong Kong
3 shared publications - Shiyuan Yang
City University of Hong Kong, Hong Kong, China
3 shared publications - Wenbin Li
Nanjing University
3 shared publications - Xiaodong Chen
Tianjin University, Tianjin, China
2 shared publications
Latest Publications
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-11
Semantic-Structural Alignment for Generative Pictorial Charts
Traditional statistical graphics are precise but often lack the visual appeal, memorability, and engagement of pictorial charts. We present a generative framework for the automated synthesis of pictorial charts that bridges the gap between semantic expression and structural faithfulness. Rather than treating charts merely as images to be stylized, we frame the problem as a dual-conditioned generation task guided by two parallel external control signals: a text prompt capturing the semantic context of the editing intent, and a context image providing the abstract statistical chart's global structure. To reinforce these controls within a Multi-Modal Diffusion Transformer, we introduce two complementary feature-level mechanisms: structural alignment to anchor spatial layouts to the input chart, and semantic alignment to transfer expressive textures from reference images. Generalizing across major visual channels (i.e., length, area, angle, and position) and diverse semantic domains, our method produces pictorial charts that are both artistically compelling and structurally consistent. Extensive quantitative evaluations and perceptual user studies demonstrate that our framework outperforms traditional controllable generation and image editing baselines, providing a foundation for high-fidelity, data-driven generative modeling in expressive visual storytelling. Project page: https://ssalign.github.io/.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-11
Open AccessSemantic-Structural Alignment for Generative Pictorial Charts
Traditional statistical graphics are precise but often lack the visual appeal, memorability, and engagement of pictorial charts. We present a generative framework for the automated synthesis of pictorial charts that bridges the gap between semantic expression and structural faithfulness. Rather than treating charts merely as images to be stylized, we frame the problem as a dual-conditioned generation task guided by two parallel external control signals: a text prompt capturing the semantic context of the editing intent, and a context image providing the abstract statistical chart's global structure. To reinforce these controls within a Multi-Modal Diffusion Transformer, we introduce two complementary feature-level mechanisms: structural alignment to anchor spatial layouts to the input chart, and semantic alignment to transfer expressive textures from reference images. Generalizing across major visual channels (i.e., length, area, angle, and position) and diverse semantic domains, our method produces pictorial charts that are both artistically compelling and structurally consistent. Extensive quantitative evaluations and perceptual user studies demonstrate that our framework outperforms traditional controllable generation and image editing baselines, providing a foundation for high-fidelity, data-driven generative modeling in expressive visual storytelling. Project page: https://ssalign.github.io/.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 7031-7045
MultiPaint: A Unified Framework for Multi-Task, Multi-Object, and Multi-Condition Video Inpainting
Video inpainting modifies local regions in video while ensuring spatial and temporal coherence. However, existing methods-both traditional and recent diffusion-based ones-face key limitations: they lack unified support for both insertion and completion, and are restricted to single-object inpainting, making it difficult to handle multi-object scenarios involving grounding and interaction. In this article, we propose MultiPaint, a unified framework for multi-task, multi-object, and multi-condition video inpainting. First, we introduce dual-branch adapters to unify the insertion and completion tasks within a single model. Moreover, we propose a test-time scheduled feature composition strategy that enables multi-object inpainting with user-specified locations while better preserving interactions among objects, a setting that has been insufficiently addressed in prior work. Additionally, we introduce a multi-condition inpainting scheme that integrates text-guided, image-guided, and keyframe-guided modes via dynamic frame masking, providing more controllability in appearance customization. Extensive experiments show that MultiPaint achieves state-of-the-art performance on object insertion and scene completion among the recent works. We further demonstrate its versatility in downstream tasks including grounded video generation, object editing, object removal, image-guided inpainting, and long video inpainting.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 7031-7045
MultiPaint: A Unified Framework for Multi-Task, Multi-Object, and Multi-Condition Video Inpainting
Video inpainting modifies local regions in video while ensuring spatial and temporal coherence. However, existing methods-both traditional and recent diffusion-based ones-face key limitations: they lack unified support for both insertion and completion, and are restricted to single-object inpainting, making it difficult to handle multi-object scenarios involving grounding and interaction. In this article, we propose MultiPaint, a unified framework for multi-task, multi-object, and multi-condition video inpainting. First, we introduce dual-branch adapters to unify the insertion and completion tasks within a single model. Moreover, we propose a test-time scheduled feature composition strategy that enables multi-object inpainting with user-specified locations while better preserving interactions among objects, a setting that has been insufficiently addressed in prior work. Additionally, we introduce a multi-condition inpainting scheme that integrates text-guided, image-guided, and keyframe-guided modes via dynamic frame masking, providing more controllability in appearance customization. Extensive experiments show that MultiPaint achieves state-of-the-art performance on object insertion and scene completion among the recent works. We further demonstrate its versatility in downstream tasks including grounded video generation, object editing, object removal, image-guided inpainting, and long video inpainting.
- 8 November 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 262
REST: A resolution preserving network for photorealistic style transfer via semantic distillation
- 8 November 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 262
REST: A resolution preserving network for photorealistic style transfer via semantic distillation
- 1 August 2025
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 26 (8) , 1428-1440
Few-shot exemplar-driven inpainting with parameter-efficient diffusion fine-tuning
Text-to-image diffusion models have demonstrated impressive capabilities in image generation and have been effectively applied to image inpainting. While t
- 1 August 2025
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 26 (8) , 1428-1440
Few-shot exemplar-driven inpainting with parameter-efficient diffusion fine-tuning
Text-to-image diffusion models have demonstrated impressive capabilities in image generation and have been effectively applied to image inpainting. While t
- 7 November 2024
- Published by Springer Nature
- p. 462-476
Task-Aware Few-Shot Image Generation via Dynamic Local Distribution Estimation and Sampling
- 7 November 2024
- Published by Springer Nature
- p. 462-476
Task-Aware Few-Shot Image Generation via Dynamic Local Distribution Estimation and Sampling
- Open Access
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-15
Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model
Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL has limitations in its ability to generalize to unseen tasks and requires the collection of a diverse task dataset. On the other hand, existing methods in the inference-based visual ICL category solely rely on textual prompts, which fail to capture fine-grained contextual information from given examples and can be time-consuming when converting from images to text prompts. To address these challenges, we propose Analogist, a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques using a text-to-image diffusion model pretrained for image inpainting. For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples. For textual prompting, we leverage GPT-4V's visual reasoning capability to efficiently generate text prompts and introduce a cross-attention masking (CAM) operation to enhance the accuracy of semantic-level analogy guided by text prompts. Our method is out-of-the-box and does not require fine-tuning or optimization. It is also generic and flexible, enabling a wide range of visual tasks to be performed in an in-context manner. Extensive experiments demonstrate the superiority of our method over existing approaches, both qualitatively and quantitatively. Our project webpage is available at https://analogist2d.github.io.
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-15
Open AccessAnalogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model
Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL has limitations in its ability to generalize to unseen tasks and requires the collection of a diverse task dataset. On the other hand, existing methods in the inference-based visual ICL category solely rely on textual prompts, which fail to capture fine-grained contextual information from given examples and can be time-consuming when converting from images to text prompts. To address these challenges, we propose Analogist, a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques using a text-to-image diffusion model pretrained for image inpainting. For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples. For textual prompting, we leverage GPT-4V's visual reasoning capability to efficiently generate text prompts and introduce a cross-attention masking (CAM) operation to enhance the accuracy of semantic-level analogy guided by text prompts. Our method is out-of-the-box and does not require fine-tuning or optimization. It is also generic and flexible, enabling a wide range of visual tasks to be performed in an in-context manner. Extensive experiments demonstrate the superiority of our method over existing approaches, both qualitatively and quantitatively. Our project webpage is available at https://analogist2d.github.io.
- Open Access
Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model
Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL has limitations in its ability to generalize to unseen tasks and requires the collection of a diverse task dataset. On the other hand, existing methods in the inference-based visual ICL category solely rely on textual prompts, which fail to capture fine-grained contextual information from given examples and can be time-consuming when converting from images to text prompts. To address these challenges, we propose Analogist, a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques using a text-to-image diffusion model pretrained for image inpainting. For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples. For textual prompting, we leverage GPT-4V's visual reasoning capability to efficiently generate text prompts and introduce a cross-attention masking (CAM) operation to enhance the accuracy of semantic-level analogy guided by text prompts. Our method is out-of-the-box and does not require fine-tuning or optimization. It is also generic and flexible, enabling a wide range of visual tasks to be performed in an in-context manner. Extensive experiments demonstrate the superiority of our method over existing approaches, both qualitatively and quantitatively.
Open AccessAnalogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model
Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL has limitations in its ability to generalize to unseen tasks and requires the collection of a diverse task dataset. On the other hand, existing methods in the inference-based visual ICL category solely rely on textual prompts, which fail to capture fine-grained contextual information from given examples and can be time-consuming when converting from images to text prompts. To address these challenges, we propose Analogist, a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques using a text-to-image diffusion model pretrained for image inpainting. For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples. For textual prompting, we leverage GPT-4V's visual reasoning capability to efficiently generate text prompts and introduce a cross-attention masking (CAM) operation to enhance the accuracy of semantic-level analogy guided by text prompts. Our method is out-of-the-box and does not require fine-tuning or optimization. It is also generic and flexible, enabling a wide range of visual tasks to be performed in an in-context manner. Extensive experiments demonstrate the superiority of our method over existing approaches, both qualitatively and quantitatively.
- 14 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 2673-2686
CariMe: Unpaired Caricature Generation With Multiple Exaggerations
Caricature generation aims to translate real photos into caricatures with artistic styles and shape exaggerations while maintaining the identity of the subject. Different from generic image-to-image translation, drawing caricatures automatically is a more challenging task due to the existence of various spatial deformations. Previous caricature generation methods are obsessed with predicting definite image warping from a given photo while ignoring the intrinsic representation and distribution of geometric exaggerations in caricatures. This limits their ability on diverse exaggeration generation. In this paper, we generalize the caricature generation problem from instance-level warping prediction to distribution-level deformation modeling. Based on this assumption, we present the first exploration for unpaired CARIcature generation with Multiple Exaggerations (CariMe) . Technically, we propose a Multi-exaggeration Warper network to learn the distribution-level mapping from photos to facial exaggerations. This makes it possible to generate diverse and reasonable exaggerations from randomly sampled warp codes given one input photo. To better represent the facial exaggeration and produce fine-grained warping, a deformation-field-based warping method is also proposed, which captures more detailed exaggerations than previous point-based warping methods. Experiments and two perceptual studies prove the superiority of our method comparing with other state-of-the-art methods, showing the improvement of our work on caricature generation. The source code is available at https://github.com/edward3862/CariMe-pytorch .
- 14 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 2673-2686
CariMe: Unpaired Caricature Generation With Multiple Exaggerations
Caricature generation aims to translate real photos into caricatures with artistic styles and shape exaggerations while maintaining the identity of the subject. Different from generic image-to-image translation, drawing caricatures automatically is a more challenging task due to the existence of various spatial deformations. Previous caricature generation methods are obsessed with predicting definite image warping from a given photo while ignoring the intrinsic representation and distribution of geometric exaggerations in caricatures. This limits their ability on diverse exaggeration generation. In this paper, we generalize the caricature generation problem from instance-level warping prediction to distribution-level deformation modeling. Based on this assumption, we present the first exploration for unpaired CARIcature generation with Multiple Exaggerations (CariMe) . Technically, we propose a Multi-exaggeration Warper network to learn the distribution-level mapping from photos to facial exaggerations. This makes it possible to generate diverse and reasonable exaggerations from randomly sampled warp codes given one input photo. To better represent the facial exaggeration and produce fine-grained warping, a deformation-field-based warping method is also proposed, which captures more detailed exaggerations than previous point-based warping methods. Experiments and two perceptual studies prove the superiority of our method comparing with other state-of-the-art methods, showing the improvement of our work on caricature generation. The source code is available at https://github.com/edward3862/CariMe-pytorch .