Related papers: Scene Grounding In the Wild
Narrated instructional videos often show and describe manipulations of similar objects, e.g., repairing a particular model of a car or laptop. In this work we aim to reconstruct such objects and to localize associated narrations in 3D.…
3D reconstruction is vital for applications in autonomous driving, virtual reality, augmented reality, and the metaverse. Recent advancements such as Neural Radiance Fields(NeRF) and 3D Gaussian Splatting (3DGS) have transformed the field,…
This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene…
Standard 3D reconstruction pipelines assume stationary world, therefore suffer from `ghost artifacts' whenever dynamic objects are present in the scene. Recent approaches has started tackling this issue, however, they typically either only…
In recent years, 3D generation has made great strides in both academia and industry. However, generating 3D scenes from a single RGB image remains a significant challenge, as current approaches often struggle to ensure both object…
Image alignment and image restoration are classical computer vision tasks. However, there is still a lack of datasets that provide enough data to train and evaluate end-to-end deep learning models. Obtaining ground-truth data for image…
This study addresses the challenge of generating online 3D Gaussian Splatting (3DGS) models from RGB-only frames. Previous studies have employed dense SLAM techniques to estimate 3D scenes from keyframes for 3DGS model construction.…
Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, single-platform constraints, and small scale. We introduce…
Novel view synthesis has evolved rapidly, advancing from Neural Radiance Fields to 3D Gaussian Splatting (3DGS), which offers real-time rendering and rapid training without compromising visual fidelity. However, 3DGS relies heavily on…
Building an efficient and physically consistent world model from limited observations is a long standing challenge in vision and robotics. Many existing world modeling pipelines are based on implicit generative models, which are hard to…
Reconstructing a dynamic scene from image inputs is a fundamental computer vision task with many downstream applications. Despite recent advancements, existing approaches still struggle to achieve high-quality reconstructions from unseen…
Acquiring 3D geometry of real world objects has various applications in 3D digitization, such as navigation and content generation in virtual environments. Image remains one of the most popular media for such visual tasks due to its…
Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…
3D scene reconstruction under unposed sparse viewpoints is a highly challenging yet practically important problem, especially in outdoor scenes due to complex lighting and scale variation. With extremely limited input views, directly…
Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time. However, leveraging 3D Gaussians for surface reconstruction poses…
Reconstructing large-scale urban scenes from sparse aerial views is a crucial yet challenging task. Due to biased top-down and shallow-oblique camera poses, sparse aerial captures exhibit strong evidence imbalance: roofs and open regions…
Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction works struggle to recover accurate scene geometry when the input views are extremely sparse. To address this issue, we…
Target localization is a prerequisite for embodied tasks such as navigation and manipulation. Conventional approaches rely on constructing explicit 3D scene representations to enable target localization, such as point clouds, voxel grids,…
Existing methods for reconstructing interactive scenes primarily focus on replacing reconstructed objects with CAD models retrieved from a limited database, resulting in significant discrepancies between the reconstructed and observed…
Recent 3D Gaussian Splatting (3DGS) representations have demonstrated remarkable performance in novel view synthesis; further, material-lighting disentanglement on 3DGS warrants relighting capabilities and its adaptability to broader…