Related papers: Sim2Real Docs: Domain Randomization for Documents …
Previous attempts to integrate Neural Radiance Fields (NeRF) into the Simultaneous Localization and Mapping (SLAM) framework either rely on the assumption of static scenes or require the ground truth camera poses, which impedes their…
We study the problem of estimating optical flow from event cameras. One important issue is how to build a high-quality event-flow dataset with accurate event values and flow labels. Previous datasets are created by either capturing real…
This paper introduces a novel pipeline for generating large-scale, highly realistic, and automatically labeled datasets for computer vision tasks in robotic environments. Our approach addresses the critical challenges of the domain gap…
We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a…
One core challenge in the development of automated vehicles is their capability to deal with a multitude of complex trafficscenarios with many, hard to predict traffic participants. As part of the iterative development process, it is…
Image synthesis driven by computer graphics achieved recently a remarkable realism, yet synthetic image data generated this way reveals a significant domain gap with respect to real-world data. This is especially true in autonomous driving…
This paper covers the time consuming issues intrinsic to physically-based image rendering algorithms. First, glass materials optical properties were measured on samples of real glasses and other objects materials inside an hotel room were…
Service robots should be able to interact naturally with non-expert human users, not only to help them in various tasks but also to receive guidance in order to resolve ambiguities that might be present in the instruction. We consider the…
We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis. We study the behavior…
Embodied reasoning is inherently viewpoint-dependent: what is visible, occluded, or reachable depends critically on where the agent stands. However, existing spatial memory systems for embodied agents typically store either multi-view…
Digital zoom on smartphones relies on learning-based super-resolution (SR) models that operate on RAW sensor images, but obtaining sensor-specific training data is challenging due to the lack of ground-truth images. Synthetic data…
Image harmonization has been significantly advanced with large-scale harmonization dataset. However, the current way to build dataset is still labor-intensive, which adversely affects the extendability of dataset. To address this problem,…
We introduce a novel approach that takes a single semantic mask as input to synthesize multi-view consistent color images of natural scenes, trained with a collection of single images from the Internet. Prior works on 3D-aware image…
Photo realism in computer generated imagery is crucially dependent on how well an artist is able to recreate real-world materials in the scene. The workflow for material modeling and editing typically involves manual tweaking of material…
Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising…
Recent progress in robot learning has been driven by large-scale datasets and powerful visuomotor policy architectures, yet policy robustness remains limited by the substantial cost of collecting diverse demonstrations, particularly for…
Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - a photo-realistic synthetic dataset consisting of more than 100,000 4K images of more than 20 types of micro aerial vehicles (MAVs). The…
We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages to real-world document segmentation. DDR renders pseudo-document…
Realistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather…
In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains. For instance, given a sketch of an object, a model needs to retrieve a real image of it from an online store's…