Related papers: World-Shaper: A Unified Framework for 360{\deg} Pa…
We present the first self-supervised method to train panoramic room layout estimation models without any labeled data. Unlike per-pixel dense depth that provides abundant correspondence constraints, layout representation is sparse and…
Given a single RGB panorama, the goal of 3D layout reconstruction is to estimate the room layout by predicting the corners, floor boundary, and ceiling boundary. A common approach has been to use standard convolutional networks to predict…
We present a method to synthesize novel views from a single $360^\circ$ panorama image based on the neural radiance field (NeRF). Prior studies in a similar setting rely on the neighborhood interpolation capability of multi-layer…
In panorama understanding, the widely used equirectangular projection (ERP) entails boundary discontinuity and spatial distortion. It severely deteriorates the conventional CNNs and vision Transformers on panoramas. In this paper, we…
Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes. However, existing methods select only informative and relevant views using…
Scene understanding and reasoning has been a fundamental problem in 3D computer vision, requiring models to identify objects, their properties, and spatial or comparative relationships among the objects. Existing approaches enable this by…
This paper presents a new approach for synthesizing a novel street-view panorama given an overhead satellite image. Taking a small satellite image patch as input, our method generates a Google's omnidirectional street-view type panorama, as…
Viewpoint missing of objects is common in scene reconstruction, as camera paths typically prioritize capturing the overall scene structure rather than individual objects. This makes it highly challenging to achieve high-fidelity…
Colour is one of the most perceptually salient yet least controllable attributes in image generation. Although recent diffusion models can modify object colours from user instructions, their results often deviate from the intended hue,…
Large-scale text-to-image models enable a wide range of image editing techniques, using text prompts or even spatial controls. However, applying these editing methods to multi-view images depicting a single scene leads to 3D-inconsistent…
Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essential for perception and interaction. Existing approaches have…
Using convolutional neural networks for 360images can induce sub-optimal performance due to distortions entailed by a planar projection. The distortion gets deteriorated when a rotation is applied to the 360image. Thus, many researches…
A single Panorama can be drawn perspectively without distortions in arbitrary viewing directions and field-of-views when the camera position is at the origin. This is a key advantage in VR and virtual tour applications because it enables…
In this paper, we propose a novel procedure for 3D layout recovery of indoor scenes from single 360 degrees panoramic images. With such images, all scene is seen at once, allowing to recover closed geometries. Our method combines…
In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360{\deg} imagery. To…
Recent advances in image generation have led to remarkable improvements in synthesizing perspective images. However, these models still struggle with panoramic image generation due to unique challenges, including varying levels of geometric…
Human perception for effective object tracking in 2D video streams arises from the implicit use of prior 3D knowledge and semantic reasoning. In contrast, most generic object tracking (GOT) methods primarily rely on 2D features of the…
World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current embodied world models…
Face reenactment and portrait relighting are essential tasks in portrait editing, yet they are typically addressed independently, without much synergy. Most face reenactment methods prioritize motion control and multiview consistency, while…
Neural fields are receiving increased attention as a geometric representation due to their ability to compactly store detailed and smooth shapes and easily undergo topological changes. Compared to classic geometry representations, however,…