Related papers: RegionE: Adaptive Region-Aware Generation for Effi…
Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to the high dimensionality of this task, most existing approaches…
Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…
Image paragraph generation is the task of producing a coherent story (usually a paragraph) that describes the visual content of an image. The problem nevertheless is not trivial especially when there are multiple descriptive and diverse…
Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are now used to improve…
With the recent advances in complex networks theory, graph-based techniques for image segmentation has attracted great attention recently. In order to segment the image into meaningful connected components, this paper proposes an image…
Exposure correction aims to enhance images suffering from improper exposure to achieve satisfactory visual effects. Despite recent progress, existing methods generally mitigate either overexposure or underexposure in input images, and they…
Existing manifold learning methods are not appropriate for image retrieval task, because most of them are unable to process query image and they have much additional computational cost especially for large scale database. Therefore, we…
Recent developments in the field of diffusion models have demonstrated an exceptional capacity to generate high-quality prompt-conditioned image edits. Nevertheless, previous approaches have primarily relied on textual prompts for image…
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…
By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…
Many current works directly adopt multi-rate depth-wise dilated convolutions to capture multi-scale contextual information simultaneously from one input feature map, thus improving the feature extraction efficiency for real-time semantic…
Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain attributes and target labels in training data. These biases are…
We propose a machine learning framework to accelerate numerical computations of time-dependent ODEs and PDEs. Our method is based on recasting (generalizations of) existing numerical methods as artificial neural networks, with a set of…
Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…
Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into one framework, we…
Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency. Some researchers have begun exploring pre-training directly…
Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while…
Image composition plays a common but important role in photo editing. To acquire photo-realistic composite images, one must adjust the appearance and visual style of the foreground to be compatible with the background. Existing deep…
A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…
Conformal prediction provides machine learning models with prediction sets that offer theoretical guarantees, but the underlying assumption of exchangeability limits its applicability to time series data. Furthermore, existing approaches…