Related papers: RoboLight: A Dataset with Linearly Composable Illu…
This paper presents Ev-Layout, a novel large-scale event-based multi-modal dataset designed for indoor layout estimation and tracking. Ev-Layout makes key contributions to the community by: Utilizing a hybrid data collection platform (with…
Building robots that can automate labor-intensive tasks has long been the core motivation behind the advancements in computer vision and the robotics community. Recent interest in leveraging 3D algorithms, particularly neural fields, has…
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…
Visual augmentation has become a crucial technique for enhancing the visual robustness of imitation learning. However, existing methods are often limited by prerequisites such as camera calibration or the need for controlled environments…
We present a first of its kind dataset of overhead imagery for development and evaluation of forensic tools. Our dataset consists of real, fully synthetic and partially manipulated overhead imagery generated from a custom diffusion model…
We introduce OLATverse, a large-scale dataset comprising around 9M images of 765 real-world objects, captured from multiple viewpoints under a diverse set of precisely controlled lighting conditions. While recent advances in object-centric…
Transparent objects are common in our daily life and frequently handled in the automated production line. Robust vision-based robotic grasping and manipulation for these objects would be beneficial for automation. However, the majority of…
In this paper, we propose the first framework that leverages physically-based inverse rendering for novel lighting generation on existing real-world human demonstrations of robotic manipulation tasks. Specifically, inverse rendering…
Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on generating details from the LR RGB…
Synthetic data generated by video generative models has shown promise for robot learning as a scalable pipeline, but it often suffers from inconsistent action quality due to imperfectly generated videos. Recently, vision-language models…
Illumination and texture editing are critical dimensions for world-to-world transfer, which is valuable for applications including sim2real and real2real visual data scaling up for embodied AI. Existing techniques generatively re-render the…
The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. However, creating such datasets is challenging: collecting…
We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to changes in environmental lighting conditions. Using a…
We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured…
We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial…
This paper addresses the challenges of data scarcity and high acquisition costs in training robust object detection models for complex industrial environments, such as offshore oil platforms. Data collection in these hazardous settings…
Low-light environments pose significant challenges for image enhancement methods. To address these challenges, in this work, we introduce the HUE dataset, a comprehensive collection of high-resolution event and frame sequences captured in…
The goal of image harmonization is adjusting the foreground appearance in a composite image to make the whole image harmonious. To construct paired training images, existing datasets adopt different ways to adjust the illumination…
Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this…
Low-light videos often exhibit spatiotemporally incoherent noise, compromising visibility and degrading performance in computer vision applications. A major challenge for enhancing such content using deep learning lies in the scarcity of…