This article provides a comprehensive survey on pioneer and state-of-the-art 3D scene
geometry estimation methodologies based on single, two, or multiple images captured …

The use of pretrained backbones with fine-tuning has been successful for 2D vision and
natural language processing tasks, showing advantages over task-specific networks. In this …

Abstract 3D room layout estimation by a single panorama using deep neural networks has
made great progress. However, previous approaches can not obtain efficient geometry …

Omnidirectional images and videos are widespread due to the popularization of devices for
capturing and visualization. Unlike pinhole-based imagery, omnidirectional media lie on the …

Indoor 360 panoramas have two essential properties.(1) The panoramas are continuous
and seamless in the horizontal direction.(2) Gravity plays an important role in indoor …

The paper studies planar surface reconstruction of indoor scenes from two views with
unknown camera poses. While prior approaches have successfully created object-centric …

Room layout estimation is a long-existing robotic vision task that benefits both environment
sensing and motion planning. However, layout estimation using point clouds (PCs) still …

Abstract Generative models eg Stable Diffusion have enabled the creation of photorealistic
images from text prompts. Yet the generation of 360-degree panorama images from text …

Vision-language navigation (VLN) requires an agent to navigate through an 3D environment
based on visual observations and natural language instructions. It is clear that the pivotal …

Recovering the 3D shape of the bounding permanent surfaces of a room from a single
image is a key component of indoor reconstruction pipelines. In this article, we introduce a …