Related papers: Seeing enough: non-reference perceptual resolution…
We introduce an efficient video segmentation system for resource-limited edge devices leveraging heterogeneous compute. Specifically, we design network models by searching across multiple dimensions of specifications for the neural…
Diffusion models have achieved remarkable success in image generation, yet their training is predominantly driven by full-reference objectives that enforce pixel-wise similarity to ground-truth images.Such supervision, while effective for…
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…
We address the problem of efficiently compressing video for conferencing-type applications. We build on recent approaches based on image animation, which can achieve good reconstruction quality at very low bitrate by representing face…
Compressive sensing (CS) works to acquire measurements at sub-Nyquist rate and recover the scene images. Existing CS methods always recover the scene images in pixel level. This causes the smoothness of recovered images and lack of…
Non-reference metrics (NRMs) can assess the visual quality of images and videos without a reference, making them well-suited for the evaluation of user-generated content. Nonetheless, rate-distortion optimization (RDO) in video coding is…
Implicit neural representations for videos (NeRV) have shown strong potential for video compression. However, applying NeRV to high-resolution 360-degree videos causes high memory usage and slow decoding, making real-time applications…
Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a…
Attribute-aware sequential recommendation entails predicting the next item a user will interact with based on a chronologically ordered history of past interactions, enriched with item attributes. Existing methods typically leverage…
Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…
Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information…
Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the…
Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…
Perceptual image quality assessment (IQA) is the task of predicting the visual quality of an image as perceived by a human observer. Current state-of-the-art techniques are based on deep representations trained in discriminative manner.…
Human visual sensitivity to spatial details declines towards the periphery. Novel image synthesis techniques, so-called foveated rendering, exploit this observation and reduce the spatial resolution of synthesized images for the periphery,…
Video streaming often requires transcoding content into different resolutions and bitrates to match the recipient's internet speed and screen capabilities. Video encoders like x264 offer various presets, each with different tradeoffs…
Image codecs are typically optimized to trade-off bitrate \vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image…
Video computer vision systems face substantial computational burdens arising from two fundamental challenges: eliminating unnecessary processing and reducing temporal redundancy in back-end inference while maintaining accuracy with minimal…
In recent years, the field of learned video compression has witnessed rapid advancement, exemplified by the latest neural video codecs DCVC-DC that has outperformed the upcoming next-generation codec ECM in terms of compression ratio.…
While humans can effortlessly transform complex visual scenes into simple words and the other way around by leveraging their high-level understanding of the content, conventional or the more recent learned image compression codecs do not…