Author name cluster

Xinglong Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ICML Conference 2025 Conference Paper

Decomposition of Graphic Design with Unified Multimodal Model

Hui Nie 0001
Zhao Zhang
Yutao Cheng
Maoke Yang
Gonglei Shi
Qingsong Xie
Jie Shao
Xinglong Wu

We propose Layer Decomposition of Graphic Designs (LDGD), a novel vision task that converts composite graphic design (e. g. , posters) into structured representations comprising ordered RGB-A layers and metadata. By transforming visual content into structured data, LDGD facilitates precise image editing and offers significant advantages for digital content creation, management, and reuse. This task presents two core challenges: (1) predicting the attribute information (metadata) of each layer, and (2) recovering the occluded regions within overlapping layers to enable high-fidelity image reconstruction. To address this, we present the Decompose Layer Model (DeaM), a large unified multimodal model that integrates a conjoined visual encoder, a language model, and a condition-aware RGB-A decoder. DeaM adopts a two-stage processing pipeline: first generates layer-specific metadata containing information such as spatial coordinates and quantized encodings, and then reconstructs pixel-accurate layer images using a condition-aware RGB-A decoder. Beyond full decomposition, the model supports interactive decomposition via textual or point-based prompts. Extensive experiments demonstrate the effectiveness of the proposed method. The code is accessed at https: //github. com/witnessai/DeaM.

Details

EAAI Journal 2025 Journal Article

Development of residual learning in deep neural networks for computer vision: A survey

Guoping Xu
Xiaxia Wang
Xinglong Wu
Xuesong Leng
Yongchao Xu

Deep neural networks (DNNs) have significantly advanced computer vision tasks such as image classification, object detection, and semantic segmentation. Residual learning, a key principle in DNN design, plays a crucial role in optimizing training and improving model performance. By incorporating skip connections, residual learning enables more efficient optimization, resulting in better accuracy during both training and testing. While many surveys have addressed specific deep learning techniques, the role of residual learning in shaping the future of DNNs for computer vision remains underexplored. This survey provides a comprehensive overview of the evolution and impact of skip connections in DNNs. We introduce the core concepts of residual learning, explore theoretical and experimental evidence supporting its effectiveness, and discuss its implications for future research directions. Additionally, we review key papers, models, datasets, and applications of residual learning across image classification, object detection, semantic segmentation, and image reconstruction. We hope this survey will inspire further exploration and innovation in residual learning techniques, both for applications of artificial intelligence in engineering and for theoretical advancements. The project page can be found at ResidualLearningSurvey.

Details DOI

NeurIPS Conference 2025 Conference Paper

DreamLight: Towards Harmonious and Consistent Image Relighting

Yong Liu
Wenpeng Xiao
Qianqian Wang
Junlin Chen
Shiyin Wang
Yitong Wang
Xinglong Wu
Yansong Tang

We introduce a model named DreamLight for universal image relighting in this work, which can seamlessly composite subjects into a new background while maintaining aesthetic uniformity in terms of lighting and color tone. The background can be specified by natural images (image-based relighting) or generated from unlimited text prompts (text-based relighting). Existing studies primarily focus on image-based relighting, while with scant exploration into text-based scenarios. Some works employ intricate disentanglement pipeline designs relying on environment maps to provide relevant information, which grapples with the expensive data cost required for intrinsic decomposition and light source. Other methods take this task as an image translation problem and perform pixel-level transformation with autoencoder architecture. While these methods have achieved decent harmonization effects, they struggle to generate realistic and natural light interaction effects between the foreground and background. To alleviate these challenges, we reorganize the input data into a unified format and leverage the semantic prior provided by the pretrained diffusion model to facilitate the generation of natural results. Moreover, we propose a Position-Guided Light Adapter (PGLA) that condenses light information from different directions in the background into designed light query embeddings, and modulates the foreground with direction-biased masked attention. In addition, we present a post-processing module named Spectral Foreground Fixer (SFF) to adaptively reorganize different frequency components of subject and relighted background, which helps enhance the consistency of foreground appearance. Extensive comparisons and user study demonstrate that our DreamLight achieves remarkable relighting performance.

PDF Details

AAAI Conference 2025 Conference Paper

Graphic Design with Large Multimodal Model

Yutao Cheng
Zhao Zhang
Maoke Yang
Hui Nie
Chunyuan Li
Xinglong Wu
Jie Shao

In the field of graphic design, automating the integration of design elements into a cohesive multi-layered artwork not only boosts productivity but also paves the way for the democratization of graphic design. One existing practice is Graphic Layout Generation (GLG), which aims to layout sequential design elements. It has been constrained by the necessity for a predefined correct sequence of layers, thus limiting creative potential and increasing user workload. In this paper, we present Hierarchical Layout Generation (HLG) as a more flexible and pragmatic setup, which creates graphic composition from any-ordered sets of design elements. To tackle the HLG task, we introduce Graphist, the first layout generation model based on large multimodal models. Graphist efficiently reframes the HLG as a sequence generation problem, utilizing RGB-A images as input, outputs a JSON draft protocol, indicating the coordinates, size, and order of each element. We develop multiple evaluation metrics for HLG. Graphist outperforms prior arts and establishes a strong baseline for this field.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation

Bowen Chen
Brynn zhao
Haomiao Sun
Li Chen
Xu Wang
Daniel Du
Xinglong Wu

Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from attribute entanglement. To overcome these challenges, we propose a novel multi-subject controlled generation model XVerse. By transforming reference images into offsets for token-specific text-stream modulation, XVerse allows for precise and independent control for specific subject without disrupting image latents or features. Consequently, XVerse offers high-fidelity, editable multi-subject image synthesis with robust control over individual subject characteristics and semantic attributes. This advancement significantly improves personalized and complex scene generation capabilities.

PDF Details