Abstract Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information important for high‐quality generation. We introduce an edge‐preserving diffusion process that generalizes isotropic models via a hybrid noise scheme with an edge‐aware scheduler that smoothly transitions from edge‐preserving to isotropic noise. This enables the model to capture fine structural details while generally maintaining global performance. We evaluate the impact of structure‐aware noise in both diffusion and flow‐matching frameworks, and show that existing isotropic models can be efficiently fine‐tuned with edge‐preserving noise, making our framework practical for adapting pre‐trained systems. Beyond unconditional generation, our method particularly shows improvements in structure‐guided tasks such as stroke‐to‐image synthesis, improving robustness and perceptual quality, as evidenced by consistent improvements across FID, KID, and CLIP‐score.

Point patterns are characterized by their density and correlation. While spatial variation of density is well-understood, analysis and synthesis of spatially-varying correlation is an open challenge. No tools are available to intuitively edit such point patterns, primarily due to the lack of a compact representation for spatially varying correlation. We propose a low-dimensional perceptual embedding for point correlations. This embedding can map point patterns to common three-channel raster images, enabling manipulation with off-the-shelf image editing software. To synthesize back point patterns, we propose a novel edge-aware objective that carefully handles sharp variations in density and correlation. The resulting framework allows intuitive and backward-compatible manipulation of point patterns, such as recoloring, relighting to even texture synthesis that have not been available to 2D point pattern design before. Effectiveness of our approach is tested in several user experiments. Code is available at https://github.com/xchhuang/patternshop.

Abstract Point pattern synthesis requires capturing both local and non‐local correlations from a given exemplar. Recent works employ deep hierarchical representations from VGG‐19 [SZ15] convolutional network to capture the features for both point‐pattern and texture synthesis. In this work, we develop a simplified optimization pipeline that uses more traditional Gabor transform‐based features. These features when convolved with simple random filters gives highly expressive feature maps. The resulting framework requires significantly less feature maps compared to VGG‐19‐based methods [TLH19; RGF∗20], better captures both the local and non‐local structures, does not require any specific data set training and can easily extend to handle multi‐class and multi‐attribute point patterns, e.g., disk and other element distributions. To validate our pipeline, we perform qualitative and quantitative analysis on a large variety of point patterns to demonstrate the effectiveness of our approach. Finally, to better understand the impact of random filters, we include a spectral analysis using filters with different frequency bandwidths.

Abstract Creative processes of artists often start with hand‐drawn sketches illustrating an object. Pre‐visualizing these keyframes is especially challenging when applied to volumetric materials such as smoke. The authored 3D density volumes must capture realistic flow details and turbulent structures, which is highly non‐trivial and remains a manual and time‐consuming process. We therefore present a method to compute a 3D smoke density field directly from 2D artist sketches, bridging the gap between early‐stage prototyping of smoke keyframes and pre‐visualization. From the sketch inputs, we compute an initial volume estimate and optimize the density iteratively with an updater CNN. Our differentiable sketcher is embedded into the end‐to‐end training, which results in robust reconstructions. Our training data set and sketch augmentation strategy are designed such that it enables general applicability. We evaluate the method on synthetic inputs and sketches from artists depicting both realistic smoke volumes and highly non‐physical smoke shapes. The high computational performance and robustness of our method at test time allows interactive authoring sessions of volumetric density fields for rapid prototyping of ideas by novice users.

Different subjects may express a specific expression in different ways due to inter-subject variabilities. In this work, besides training deep-learned facial expression feature (emotional feature), we also consider the influence of latent face identity feature such as the shape or appearance of face. We propose an identity and emotion joint learning approach with deep convolutional neural networks (CNNs) to enhance the performance of facial expression recognition (FER) tasks. First, we learn the emotion and identity features separately using two different CNNs with their corresponding training data. Second, we concatenate these two features together as a deep-learned Tandem Facial Expression (TFE) Feature and feed it to the subsequent fully connected layers to form a new model. Finally, we perform joint learning on the newly merged network using only the facial expression training data. Experimental results show that our proposed approach achieves 99.31 and 84.29 percent accuracy on the CK+ and the FER+ database, respectively, which outperforms the residual network baseline as well as many other state-of-the-art methods.

Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some work has also been done to transfer previously learned knowledge to the new task when the tasks are similar and have shared knowledge. %However, in the most general case, a CL system not only should have the above two capabilities, but also the \textit{backward knowledge transfer} capability so that future tasks may help improve the past models whenever possible. To the best of our knowledge, no technique has been proposed to learn a sequence of mixed similar and dissimilar tasks that can deal with forgetting and also transfer knowledge forward and backward. This paper proposes such a technique to learn both types of tasks in the same network. For dissimilar tasks, the algorithm focuses on dealing with forgetting, and for similar tasks, the algorithm focuses on selectively transferring the knowledge learned from some similar previous tasks to improve the new task learning. Additionally, the algorithm automatically detects whether a new task is similar to any previous tasks. Empirical evaluation using sequences of mixed tasks demonstrates the effectiveness of the proposed model.

Cross-domain sentiment classification aims to tag sentiments for a target domain by labeled data from a source domain. Due to the difference between domains, the accuracy of a trained classifier may be very low. In this paper, we propose a boosting-based learning framework named TR-TrAdaBoost for cross-domain sentiment classification. We firstly explore the topic distribution of documents, and then combine it with the unigram TrAdaBoost. The topic distribution captures the domain information of documents, which is valuable for cross-domain sentiment classification. Experimental results indicate that TR-TrAdaBoost represents documents well and boost the performance and robustness of TrAdaBoost.