Related papers: Parameter-Free Neural Lens Blur Rendering for High…

This paper presents an uncalibrated deep neural network framework for the photometric stereo problem. For training models to solve the problem, existing neural network-based methods either require exact light directions or ground-truth…

Bokeh is an important artistic effect used to highlight the main object of interest on the photo by blurring all out-of-focus areas. While DSLR and system camera lenses can render this effect naturally, mobile cameras are unable to produce…

Camera calibration is a necessity in various tasks including 3D reconstruction, hand-eye coordination for a robotic interaction, autonomous driving, etc. In this work we propose a novel method to predict extrinsic (baseline, pitch, and…

Images taken in a low light condition with the presence of camera shake suffer from motion blur and photon shot noise. While state-of-the-art image restoration networks show promising results, they are largely limited to well-illuminated…

The new generation of deep photometric surveys requires unprecedentedly precise shape and photometry measurements of billions of galaxies to achieve their main science goals. At such depths, one major limiting factor is the blending of…

We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. We integrate a learning-based depth prior, in the form of a convolutional neural network trained for single-image depth estimation,…

Image Super-Resolution (SR) provides a promising technique to enhance the image quality of low-resolution optical sensors, facilitating better-performing target detection and autonomous navigation in a wide range of robotics applications.…

Realistic indoor or outdoor image synthesis is a core challenge in computer vision and graphics. The learning-based approach is easy to use but lacks physical consistency, while traditional Physically Based Rendering (PBR) offers high…

Intrinsic decomposition is a fundamental mid-level vision problem that plays a crucial role in various inverse rendering and computational photography pipelines. Generating highly accurate intrinsic decompositions is an inherently…

Image compositing is a task of combining regions from different images to compose a new image. A common use case is background replacement of portrait images. To obtain high quality composites, professionals typically manually perform…

Object compositing offers significant promise for augmented reality (AR) and embodied intelligence applications. Existing approaches predominantly focus on single-image scenarios or intrinsic decomposition techniques, facing challenges with…

Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image…

In natural image matting, the goal is to estimate the opacity of the foreground object in the image. This opacity controls the way the foreground and background is blended in transparent regions. In recent years, advances in deep learning…

Low-light image enhancement - a pervasive but challenging problem, plays a central role in enhancing the visibility of an image captured in a poor illumination environment. Due to the fact that not all photons can pass the Bayer-Filter on…

Digital image forensics aims to detect images that have been digitally manipulated. Realistic image forgeries involve a combination of splicing, resampling, region removal, smoothing and other manipulation methods. While most detection…

Depth map fusion is an essential part in both stereo and RGB-D based 3-D reconstruction pipelines. Whether produced with a passive stereo reconstruction or using an active depth sensor, such as Microsoft Kinect, the depth maps have noise…

Editing a local region or a specific object in a 3D scene represented by a NeRF or consistently blending a new realistic object into the scene is challenging, mainly due to the implicit nature of the scene representation. We present…

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

It is difficult to recover the motion field from a real-world footage given a mixture of camera shake and other photometric effects. In this paper we propose a hybrid framework by interleaving a Convolutional Neural Network (CNN) and a…

3D semantic occupancy prediction is a pivotal task in the field of autonomous driving. Recent approaches have made great advances in 3D semantic occupancy predictions on a single modality. However, multi-modal semantic occupancy prediction…