Related papers: Relighting Images in the Wild with a Self-Supervis…
Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to solve specific tasks end-to-end, from pixels to torques.…
Reconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also to the new lighting…
Monocular depth estimation remains challenging, as foundation models such as Depth Anything V2 (DA-V2) struggle with real-world images that are far from the training distribution. We introduce Re-Depth Anything, a test-time self-supervision…
Image deblurring aims to restore the latent sharp images from the corresponding blurred ones. In this paper, we present an unsupervised method for domain-specific single-image deblurring based on disentangled representations. The…
Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be…
Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…
Recovering a continuous colormap from a single 2D scalar field visualization can be quite challenging, especially in the absence of a corresponding color legend. In this paper, we propose a novel colormap recovery approach that extracts the…
We propose a general framework for solving inverse problems in the presence of noise that requires no signal prior, no noise estimate, and no clean training data. We only require that the forward model be available and that the noise be…
This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex…
We address the problem of image reconstruction from incomplete measurements, encompassing both upsampling and inpainting, within a learning-based framework. Conventional supervised approaches require fully sampled ground truth data, while…
Super-resolution tasks oriented to images captured in ultra-dark environments is a practical yet challenging problem that has received little attention. Due to uneven illumination and low signal-to-noise ratio in dark environments, a…
Estimating a scene's lighting is a very important task when compositing synthetic content within real environments, with applications in mixed reality and post-production. In this work we present a data-driven model that estimates an HDR…
Intrinsic image decomposition aims at separating an image into its underlying albedo and shading components, isolating the base color from lighting effects to enable downstream applications such as virtual relighting and scene editing.…
Image inpainting is the process of regenerating lost parts of the image. Supervised algorithm-based methods have shown excellent results but have two significant drawbacks. They do not perform well when tested with unseen data. They fail to…
Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce…
While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments. Existing methods…
In the remote sensing context spectral unmixing is a technique to decompose a mixed pixel into two fundamental representatives: endmembers and abundances. In this paper, a novel architecture is proposed to perform blind unmixing on…
Recently, denoising methods based on supervised learning have exhibited promising performance. However, their reliance on external datasets containing noisy-clean image pairs restricts their applicability. To address this limitation,…
Current deep learning-based low-light image enhancement methods often struggle with high-resolution images, and fail to meet the practical demands of visual perception across diverse and unseen scenarios. In this paper, we introduce a novel…
Although deep learning are commonly employed for image recognition, usually huge amount of labeled training data is required, which may not always be readily available. This leads to a noticeable performance disparity when compared to…