Related papers: Improving Feature Stability during Upsampling -- S…
Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained…
Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, for which we solve so-called jigsaw…
We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…
Artifact detectors have been shown to enhance the performance of image-generative models by serving as reward models during fine-tuning. These detectors enable the generative model to improve overall output fidelity and aesthetics. However,…
The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in…
Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…
This paper proposes a method for unsupervised anomalous sound detection (UASD) and captioning the reason for detection. While there is a method that captions the difference between given normal and anomalous sound pairs, it is assumed to be…
As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manipulation detection, they typically require expensive…
Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a set of discrete scales or struggle to maintain good…
Image compression with upsampling encodes information to succeedingly increase image resolution, for example by encoding differences in FUIF and JPEG XL. It is useful for progressive decoding, also often can improve compression ratio - both…
Spatial sampling is traditionally studied in a static setting where static sensors scattered around space take measurements of the spatial field at their locations. In this paper we study the emerging paradigm of sampling and reconstructing…
Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts…
Semi-supervised semantic segmentation involves assigning pixel-wise labels to unlabeled images at training time. This is useful in a wide range of real-world applications where collecting pixel-wise labels is not feasible in time or cost.…
The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either…
To increase the flexibility and scalability of deep neural networks for image reconstruction, a framework is proposed based on bandpass filtering. For many applications, sensing measurements are performed indirectly. For example, in…
Purpose: Compressed sensing MRI (CS-MRI) from single and parallel coils is one of the powerful ways to reduce the scan time of MR imaging with performance guarantee. However, the computational costs are usually expensive. This paper aims to…
Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks. However, these generated images often exhibit perceptual artifacts in specific regions, necessitating manual…
Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in search and retrieval systems where it is crucial to avoid reprocessing of the gallery…
Though semantic segmentation has been heavily explored in vision literature, unique challenges remain in the remote sensing domain. One such challenge is how to handle resolution mismatch between overhead imagery and ground-truth label…
Stochastic sampling techniques are ubiquitous in real-time rendering, where performance constraints force the use of low sample counts, leading to noisy intermediate results. To remove this noise, the post-processing step of temporal and…