Related papers: A Categorized Reflection Removal Dataset with Dive…

Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling. In this paper, we investigate SR from the perspective of camera lenses, named as…

Polarization-aware Neural Radiance Fields (NeRF) enable novel view synthesis of specular-reflection scenes but face challenges in slow training, inefficient rendering, and strong dependencies on material/viewpoint assumptions. However, 3D…

We propose a novel approach that jointly removes reflection or translucent layer from a scene and estimates scene depth. The input data are captured via light field imaging. The problem is couched as minimizing the rank of the transmitted…

Grasping in cluttered scenes is challenging for robot vision systems, as detection accuracy can be hindered by partial occlusion of objects. We adopt a reinforcement learning (RL) framework and 3D vision architectures to search for feasible…

Realistic shadow generation is a critical component for high-quality image compositing and visual effects, yet existing methods suffer from certain limitations: Physics-based approaches require a 3D scene geometry, which is often…

Sun Glare widely exists in the images captured by unmanned ground and aerial vehicles performing in outdoor environments. The existence of such artifacts in images will result in wrong feature extraction and failure of autonomous systems.…

Recently, subsampling or refining images generated from unconditional GANs has been actively studied to improve the overall image quality. Unfortunately, these methods are often observed less effective or inefficient in handling conditional…

We present a means of characterizing and removing internal reflections between the CCD and other optical surfaces in an astronomical camera. The stellar reflections appear as out-of-focus images and are not necessarily axisymmetric about…

In this paper we present a dense ground truth dataset of nonrigidly deforming real-world scenes. Our dataset contains both long and short video sequences, and enables the quantitatively evaluation for RGB based tracking and registration…

Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low…

Increasing the visibility of nighttime hazy images is challenging because of uneven illumination from active artificial light sources and haze absorbing/scattering. The absence of large-scale benchmark datasets hampers progress in this…

The accuracy of face recognition systems has improved significantly in the past few years, thanks to the large amount of data collected and advancements in neural network architectures. However, these large-scale datasets are often…

Causal representation learning (CRL) models aim to transform high-dimensional data into a latent space, enabling interventions to generate counterfactual samples or modify existing data based on the causal relationships among latent…

Super-resolution (SR) has traditionally been based on pairs of high-resolution images (HR) and their low-resolution (LR) counterparts obtained artificially with bicubic downsampling. However, in real-world SR, there is a large variety of…

The clutter in the ground-penetrating radar (GPR) radargram disguises or distorts subsurface target responses, which severely affects the accuracy of target detection and identification. Existing clutter removal methods either leave…

The task of extracting intrinsic components, such as reflectance and shading, from neural radiance fields is of growing interest. However, current methods largely focus on synthetic scenes and isolated objects, overlooking the complexities…

Constructing high-quality character image datasets is challenging because real-world images are often affected by image degradation. There are limitations when applying current image restoration methods to such real-world character images,…

Single image scene relighting aims to generate a realistic new version of an input image so that it appears to be illuminated by a new target light condition. Although existing works have explored this problem from various perspectives,…

Existing raindrop removal datasets have two shortcomings. First, they consist of images captured by cameras with a focus on the background, leading to the presence of blurry raindrops. To our knowledge, none of these datasets include images…

There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from…