Related papers: $L^3$:Scene-agnostic Visual Localization in the Wi…

Developing a multi-modal language model capable of understanding 3D scenes remains challenging due to the limited availability of 3D training data, in contrast to the abundance of 2D datasets used for vision-language models (VLM). As an…

Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with…

We present 3DP3, a framework for inverse graphics that uses inference in a structured generative model of objects, scenes, and images. 3DP3 uses (i) voxel models to represent the 3D shape of objects, (ii) hierarchical scene graphs to…

Visual localization is the task of estimating the camera pose of an image relative to a scene representation. In practice, visual localization systems are often cloud-based. Naturally, this raises privacy concerns in terms of revealing…

Considering the accelerated development of Unmanned Aerial Vehicles (UAVs) applications in both industrial and research scenarios, there is an increasing need for localizing these aerial systems in non-urban environments, using GNSS-Free,…

Indoor scene synthesis aims to automatically produce plausible, realistic and diverse 3D indoor scenes, especially given arbitrary user requirements. Recently, the promising generalization ability of pre-trained large language models (LLM)…

Current feed-forward 3D/4D reconstruction systems rely on dense geometry and pose supervision -- expensive to obtain at scale and particularly scarce for dynamic real-world scenes. We present Flow3r, a framework that augments visual…

We present a complete map management process for a visual localization system designed for multi-vehicle long- term operations in resource constrained outdoor environments. Outdoor visual localization generates large amounts of data that…

This paper addresses the task of large-scale 3D scene reconstruction from long video sequences. Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D…

Reconstructing the underlying 3D surface of an object from a single image is a challenging problem that has received extensive attention from the computer vision community. Many learning-based approaches tackle this problem by learning a 3D…

Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model.…

3D visual grounding (3DVG) is challenging due to the need to understand 3D spatial relations. While supervised approaches have achieved superior performance, they are constrained by the scarcity and high annotation costs of 3D…

Stylizing 3D scenes instantly while maintaining multi-view consistency and faithfully resembling a style image remains a significant challenge. Current state-of-the-art 3D stylization methods typically involve computationally intensive…

The 3D reconstruction of simultaneous localization and mapping (SLAM) is an important topic in the field for transport systems such as drones, service robots and mobile AR/VR devices. Compared to a point cloud representation, the 3D…

Changes in appearance is one of the main sources of failure in visual localization systems in outdoor environments. To address this challenge, we present VIZARD, a visual localization system for urban outdoor environments. By combining a…

3D occupancy prediction has recently emerged as a new paradigm for holistic 3D scene understanding and provides valuable information for downstream planning in autonomous driving. Most existing methods, however, are computationally…

We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our…

Robust and accurate, map-based localization is crucial for autonomous mobile systems. In this paper, we exploit range images generated from 3D LiDAR scans to address the problem of localizing mobile robots or autonomous cars in a map of a…

Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applications such as immersive interaction and content creation. However, existing…

Modern learning-based approaches to 3D-aware image synthesis achieve high photorealism and 3D-consistent viewpoint changes for the generated images. Existing approaches represent instances in a shared canonical space. However, for…