Related papers: Omni Aggregation Networks for Lightweight Image Su…
Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous…
Light field (LF) images can be used to improve the performance of image super-resolution (SR) because both angular and spatial information is available. It is challenging to incorporate distinctive information from different views for LF…
Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-image diffusion models such as FLUX and SD3 remain confined…
Transformers have exhibited promising performance in computer vision tasks including image super-resolution (SR). However, popular transformer-based SR methods often employ window self-attention with quadratic computational complexity to…
Recent breakthroughs in Neural Radiance Fields (NeRFs) have sparked significant demand for their integration into real-world 3D applications. However, the varied functionalities required by different 3D applications often necessitate…
Independent indoor mobility remains a critical challenge for individuals with visual impairments, largely due to the limited capability of existing assistive systems in detecting fine-grained hazardous objects such as chairs, tables, and…
Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer from heavy computational burden and slow inference due to the…
This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. Unlike existing Transformer methods, which employ standard Transformer blocks to tackle…
In this paper we propose a vision system that performs image Super Resolution (SR) with selectivity. Conventional SR techniques, either by multi-image fusion or example-based construction, have failed to capitalize on the intrinsic…
Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial…
Vision Transformers (ViTs) have emerged as a powerful architecture for computer vision tasks due to their ability to model long-range dependencies and global contextual relationships. However, their substantial compute and memory demands…
Recent vision-language-action (VLA) models build upon vision-language foundations, and have achieved promising results and exhibit the possibility of task generalization in robot manipulation. However, due to the heterogeneity of tactile…
With the advent of smart devices that support 4K and 8K resolution, Single Image Super Resolution (SISR) has become an important computer vision problem. However, most super resolution deep networks are computationally very expensive. In…
Hyperspectral Imaging is the acquisition of spectral and spatial information of a particular scene. Capturing such information from a specialized hyperspectral camera remains costly. Reconstructing such information from the RGB image…
Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation. Recent advanced models either employ a discrete modeling for these…
We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design or use neural architecture search (NAS) to find a specialized…
We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (\ie, classification heads) instead of relying on channel expansion or additional building blocks. Our approach employs…
Cooperative perception can increase the view field and decrease the occlusion of an ego vehicle, hence improving the perception performance and safety of autonomous driving. Despite the success of previous works on cooperative object…
Stereo image super-resolution aims to generate high-resolution images by leveraging complementary information from binocular systems. Although previous studies have achieved impressive results, the potential of intra-view and cross-view…
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to convolutions as a plug-and-play module and embed them in…