Related papers: InfiniCity: Infinite-Scale City Synthesis
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to…
This paper proposes a method for automatic generation of textures for 3D city meshes in immersive urban environments. Many recent pipelines capture or synthesize large quantities of city geometry using scanners or procedural modeling…
Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability…
The creation of detailed 3D models is relevant for a wide range of applications such as navigation in three-dimensional space, construction planning or disaster assessment. However, the complex processing and long execution time for…
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes,…
This paper describes the Qualcomm AI Research solution to the RealADSim-NVS challenge, hosted at the RealADSim Workshop at ICCV 2025. The challenge concerns novel view synthesis in street scenes, and participants are required to generate,…
Synthesizing interactive 3D scenes from text is essential for gaming, virtual reality, and embodied AI. However, existing methods face several challenges. Learning-based approaches depend on small-scale indoor datasets, limiting the scene…
Accurate and up-to-date geospatial data are essential for urban planning, infrastructure monitoring, and environmental management. Yet, automating urban monitoring remains difficult because curated datasets of specific urban features and…
Synthetic datasets, recognized for their cost effectiveness, play a pivotal role in advancing computer vision tasks and techniques. However, when it comes to remote sensing image processing, the creation of synthetic datasets becomes…
In this paper, we propose a novel LiDAR(-inertial) odometry and mapping framework to achieve the goal of simultaneous localization and meshing in real-time. This proposed framework termed ImMesh comprises four tightly-coupled modules:…
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes. More specifically, the input layout consists of one or more…
The advancement of autonomous driving is increasingly reliant on high-quality annotated datasets, especially in the task of 3D occupancy prediction, where the occupancy labels require dense 3D annotation with significant human effort. In…
This chapter introduces OpenStreetMap - a crowd-sourced, worldwide mapping project and geospatial data repository - to illustrate its usefulness in quickly and easily analyzing and visualizing planning and design outcomes in the built…
Neural rendering has demonstrated remarkable success in high-quality 3D neural reconstruction and novel view synthesis with dense input views and accurate poses. However, applying it to extremely sparse, unposed views in unbounded 360{\deg}…
Cities are structured by roads. Having up to date and detailed maps of these is thus an important challenge for urban planing, civil engineering and transportation. Those maps are traditionally created manually, which represents a massive…
Existing text-to-3D and image-to-3D models often struggle with complex scenes involving multiple objects and intricate interactions. Although some recent attempts have explored such compositional scenarios, they still require an extensive…
Volumetric models have become a popular representation for 3D scenes in recent years. One breakthrough leading to their popularity was KinectFusion, which focuses on 3D reconstruction using RGB-D sensors. However, monocular SLAM has since…
In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting all the dynamic…
Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, we propose an end-to-end system…
We address the issue of the exploding computational requirements of recent State-of-the-art (SOTA) open set multimodel 3D mapping (dense 3D mapping) algorithms and present Voxel-Aggregated Feature Synthesis (VAFS), a novel approach to dense…