Related papers: Human-centric Indoor Scene Synthesis Using Stochas…

We consider the problem of learning object arrangements in a 3D scene. The key idea here is to learn how objects relate to human poses based on their affordances, ease of use and reachability. In contrast to modeling object-object…

In this paper, we propose Text2Scene, a model that generates various forms of compositional scene representations from natural language descriptions. Unlike recent works, our method does NOT use Generative Adversarial Networks (GANs).…

One major goal of vision is to infer physical models of objects, surfaces, and their layout from sensors. In this paper, we aim to interpret indoor scenes from one RGBD image. Our representation encodes the layout of walls, which must…

In this work, we introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts, trained using single-view images. Different from most existing 3D GANs that limit their…

Estimating the geometry level of human-scene contact aims to ground specific contact surface points at 3D human geometries, which provides a spatial prior and bridges the interaction between human and scene, supporting applications such as…

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a…

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…

Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent…

Recent open-vocabulary robot mapping methods enrich dense geometric maps with pre-trained visual-language features. While these maps allow for the prediction of point-wise saliency maps when queried for a certain language concept,…

We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material explanations represented as albedo, roughness, and metallic maps.…

Semantic image synthesis (SIS) aims to generate realistic images that match given semantic masks. Despite recent advances allowing high-quality results and precise spatial control, they require a massive semantic segmentation dataset for…

Class-agnostic 3D instance segmentation tackles the challenging task of segmenting all object instances, including previously unseen ones, without semantic class reliance. Current methods struggle with generalization due to the scarce…

The performance of supervised deep learning algorithms depends significantly on the scale, quality and diversity of the data used for their training. Collecting and manually annotating large amount of data can be both time-consuming and…

Word spotting in natural scene images has many applications in scene understanding and visual assistance. In this paper we propose a technique to create and exploit an intermediate representation of images based on text attributes which are…

Compositing human figures into scene images has broad applications in areas such as entertainment and advertising. However, existing methods often cannot handle occlusion of the inserted person by foreground objects and unnaturally place…

3D scene understanding plays a vital role in vision-based autonomous driving. While most existing methods focus on 3D object detection, they have difficulty describing real-world objects of arbitrary shapes and infinite classes. Towards a…

We present a novel approach for 3D indoor scene reconstruction that combines 3D Gaussian Splatting (3DGS) with mesh representations. We use meshes for the room layout of the indoor scene, such as walls, ceilings, and floors, while employing…

A crucial ability of human intelligence is to build up models of individual 3D objects from partial scene observations. Recent works achieve object-centric generation but without the ability to infer the representation, or achieve 3D scene…

Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding complex 3D scenes from limited 2D image observations. Existing SOP methods typically aggregate contextual features to assist the occupancy representation…

A large amount of annotated training images is critical for training accurate and robust deep network models but the collection of a large amount of annotated training images is often time-consuming and costly. Image synthesis alleviates…