Related papers: Parameter-Free Neural Lens Blur Rendering for High…
Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…
A depth image provides partial geometric information of a 3D scene, namely the shapes of physical objects as observed from a particular viewpoint. This information is important when synthesizing images of different virtual camera viewpoints…
Deep learning methods for perception are the cornerstone of many robotic systems. Despite their potential for impressive performance, obtaining real-world training data is expensive, and can be impractically difficult for some tasks.…
Generative image models can produce convincingly real images, with plausible shapes, textures, layouts and lighting. However, one domain in which they perform notably poorly is in the synthesis of transparent objects, which exhibit…
Neural Radiance Fields (NeRF) have demonstrated impressive performance in novel view synthesis. However, NeRF and most of its variants still rely on traditional complex pipelines to provide extrinsic and intrinsic camera parameters, such as…
Image de-blurring is important in many cases of imaging a real scene or object by a camera. This project focuses on de-blurring an image distorted by an out-of-focus blur through a simulation study. A pseudo-inverse filter is first explored…
Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only reason about areas that are visible in the image.…
This paper presents a blind detection and compensation technique for camera lens geometric distortions. The lens distortion introduces higher-order correlations in the frequency domain and in turn it can be detected using higher-order…
Illuminant estimation aims to infer scene illumination from image measurements despite intrinsic ambiguities between surface reflectance and lighting. Most existing methods operate on trichromatic RGB images and are therefore fundamentally…
A simple and inexpensive (low-power and low-bandwidth) modification is made to a conventional off-the-shelf color video camera, from which we recover {multiple} color frames for each of the original measured frames, and each of the…
This work proposes novel hyperparameter-free losses for single view 3D reconstruction with morphable models (3DMM). We dispense with the hyperparameters used in other works by exploiting geometry, so that the shape of the object and the…
The reliable fusion of depth maps from multiple viewpoints has become an important problem in many 3D reconstruction pipelines. In this work, we investigate its impact on robotic bin-picking tasks such as 6D object pose estimation. The…
We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling…
A simple, yet general, formalism for the optimized linear combination of astrophysical images is constructed and demonstrated. The formalism allows the user to combine multiple undersampled images to provide oversampled output at high…
This paper tackles the task of uncalibrated photometric stereo for 3D object reconstruction, where both the object shape, object reflectance, and lighting directions are unknown. This is an extremely difficult task, and the challenge is…
Video deblurring is a challenging problem as the blur is complex and usually caused by the combination of camera shakes, object motions, and depth variations. Optical flow can be used for kernel estimation since it predicts motion…
Image compositing is a method used to generate realistic yet fake imagery by inserting contents from one image to another. Previous work in compositing has focused on improving appearance compatibility of a user selected foreground segment…
Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate on entire images holistically, limiting the ability to isolate and manipulate…
We introduce an improved solution to the neural image-based rendering problem in computer vision. Given a set of images taken from a freely moving camera at train time, the proposed approach could synthesize a realistic image of the scene…
Camera calibration is an essential first step in setting up 3D Computer Vision systems. Commonly used parametric camera models are limited to a few degrees of freedom and thus often do not optimally fit to complex real lens distortion. In…