Yongchuan Tang

Xinlong Zhang, Jia Wei, Xiaoyu Zhang et al.

Achieving high-fidelity object-level control in Diffusion Transformers remains a significant challenge despite the introduction of structural priors like depth and Canny maps. Current object-level conditional generation methods frequently suffer from visual artifacts and struggle to maintain precise control over objects within small localized regions. To address these limitations, we propose Cascaded Object-Level Latent Refinement (COLLAR), a training-free framework that progressively optimizes object-level features via the Field-of-View (FoV) expansion. First, we propose the Cross-Scale Semantic Alignment (CSSA) module to address spatial-semantic gaps by injecting object-level features into extended-FoV branches via attention mechanisms. To further optimize these features, the Cyclic Feature Injection (CFI) module introduces a reciprocal background feedback mechanism. It leverages a frequency-based adaptive strategy to selectively update the global backbone with context-aligned local information. Finally, the extended-FoV branch serves as a hub for feature optimization, ensuring that object-level features are integrated into the global generation process without compromising final image quality. Extensive experiments on the COCO-MIG and COCO-POS benchmarks demonstrate that our approach consistently outperforms state-of-the-art methods across semantic alignment, image quality, and spatial fidelity.

Teng Zhou, Xiaoyu Zhang, Yongchuan Tang

Panoramic Image Generation (PIG) aims to create coherent images of arbitrary lengths. Most existing methods fall in the joint diffusion paradigm, but their complex and heuristic crop connection designs often limit their ability to achieve multilevel coherence. By deconstructing this challenge into its core components, we find it naturally aligns with next-token prediction, leading us to adopt an autoregressive (AR) paradigm for PIG modeling. However, existing visual AR (VAR) models are limited to fixed-size generation, lacking the capability to produce panoramic images. In this paper, we propose PanoLlama, a novel framework that achieves endless and coherent panorama generation with the autoregressive paradigm. Our approach develops a training-free strategy that utilizes token redirection to overcome the size limitations of existing VAR models, enabling next-crop prediction in both horizontal and vertical directions. This refreshes the PIG pipeline while achieving SOTA performance in coherence (47.50%), fidelity(28.16%), and aesthetics (15%). Additionally, PanoLlama supports applications other PIG methods cannot achieve, including mask-free layout control, multi-scale and multi-guidance synthesis. To facilitate standardized evaluation, we also establish a dataset with 1,000 prompts spanning 100+ themes, providing a new testing benchmark for PIG research. The code is available at https://github.com/0606zt/PanoLlama.

Teng Zhou, Yongchuan Tang

Diffusion models have emerged as effective tools for generating diverse and high-quality content. However, their capability in high-resolution image generation, particularly for panoramic images, still faces challenges such as visible seams and incoherent transitions. In this paper, we propose TwinDiffusion, an optimized framework designed to address these challenges through two key innovations: the Crop Fusion for quality enhancement and the Cross Sampling for efficiency optimization. We introduce a training-free optimizing stage to refine the similarity of adjacent image areas, as well as an interleaving sampling strategy to yield dynamic patches during the cropping process. A comprehensive evaluation is conducted to compare TwinDiffusion with the prior works, considering factors including coherence, fidelity, compatibility, and efficiency. The results demonstrate the superior performance of our approach in generating seamless and coherent panoramas, setting a new standard in quality and efficiency for panoramic image generation.

Xiaoyu Zhang, Teng Zhou, Xinlong Zhang et al.

Diffusion models have recently gained recognition for generating diverse and high-quality content, especially in image synthesis. These models excel not only in creating fixed-size images but also in producing panoramic images. However, existing methods often struggle with spatial layout consistency when producing high-resolution panoramas due to the lack of guidance on the global image layout. This paper introduces the Multi-Scale Diffusion (MSD), an optimized framework that extends the panoramic image generation framework to multiple resolution levels. Our method leverages gradient descent techniques to incorporate structural information from low-resolution images into high-resolution outputs. Through comprehensive qualitative and quantitative evaluations against prior work, we demonstrate that our approach significantly improves the coherence of high-resolution panorama generation.

Yongchuan Tang, Rongfei Li

Negation is an important perspective of knowledge representation. Existing negation methods are mainly applied in probability theory, evidence theory and complex evidence theory. As a generalization of evidence theory, random permutation sets theory may represent information more precisely. However, how to apply the concept of negation to random permutation sets theory has not been studied. In this paper, the negation of permutation mass function is proposed. Moreover, in the negation process, the convergence of proposed negation method is verified. The trends of uncertainty and dissimilarity after each negation operation are investigated. Numerical examples are used to demonstrate the rationality of the proposed method.

Miao Qin, Yongchuan Tang

This paper investigates the issues of combination and normalization of interval-valued belief structures within the framework of Dempster-Shafer theory of evidence. Existing approaches are reviewed and thoroughly analyzed. The advantages and drawbacks of previous approach are presented. A new optimality approach based on uncertainty measure is developed, where the problem of combining interval-valued belief structures degenerates into combining basic probability assignments. Numerical examples are provided to illustrate the rationality of the proposed approach.

Dongdong Wu, Zijing Liu, Yongchuan Tang

The process of information fusion needs to deal with a large number of uncertain information with multi-source, heterogeneity, inaccuracy, unreliability, and incompleteness. In practical engineering applications, Dempster-Shafer evidence theory is widely used in multi-source information fusion owing to its effectiveness in data fusion. Information sources have an important impact on multi-source information fusion in an environment of complex, unstable, uncertain, and incomplete characteristics. To address multi-source information fusion problem, this paper considers the situation of uncertain information modeling from the closed world to the open world assumption and studies the generation of basic probability assignment (BPA) with incomplete information. In this paper, a new method is proposed to generate generalized basic probability assignment (GBPA) based on the triangular fuzzy number model under the open world assumption. The proposed method can not only be used in different complex environments simply and flexibly, but also have less information loss in information processing. Finally, a series of comprehensive experiments basing on the UCI data sets are used to verify the rationality and superiority of the proposed method.

Zejian Li, Yongchuan Tang, Yongxing He

Learning the disentangled representation of interpretable generative factors of data is one of the foundations to allow artificial intelligence to think like people. In this paper, we propose the analogical training strategy for the unsupervised disentangled representation learning in generative models. The analogy is one of the typical cognitive processes, and our proposed strategy is based on the observation that sample pairs in which one is different from the other in one specific generative factor show the same analogical relation. Thus, the generator is trained to generate sample pairs from which a designed classifier can identify the underlying analogical relation. In addition, we propose a disentanglement metric called the subspace score, which is inspired by subspace learning methods and does not require supervised information. Experiments show that our proposed training strategy allows the generative models to find the disentangled factors, and that our methods can give competitive performances as compared with the state-of-the-art methods.