Related papers: TAPIP3D: Tracking Any Point in Persistent 3D Geome…
We present a unified framework capable of solving a broad range of 3D tasks. Our approach features a stateful recurrent model that continuously updates its state representation with each new observation. Given a stream of images, this…
Accurate and consistent 3D tracking from multiple cameras is a key component in a vision-based autonomous driving system. It involves modeling 3D dynamic objects in complex scenes across multiple cameras. This problem is inherently…
Reconstructing scenes and tracking motion are two sides of the same coin. Tracking points allow for geometric reconstruction [14], while geometric reconstruction of (dynamic) scenes allows for 3D tracking of points over time [24, 39]. The…
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D local feature descriptors and detectors having been proposed,…
The introduction of neural radiance fields has greatly improved the effectiveness of view synthesis for monocular videos. However, existing algorithms face difficulties when dealing with uncontrolled or lengthy scenarios, and require…
Generalist robot policies built upon 2D visual representations excel at semantic reasoning but inherently lack the explicit 3D spatial awareness required for high-precision tasks. Existing 3D integration methods struggle to bridge this gap…
Building 3D geometric maps of man-made spaces is a well-established and active field that is fundamental to computer vision and robotics. However, considering the evolving nature of built environments, it is essential to question the…
Various real-time methods for capturing and transmitting dynamic 3D spaces have been proposed, including those based on RGB-D cameras and volumetric capture. However, applying existing methods to outdoor tourist sites remains difficult…
Recent advancements in Diffusion Transformer (DiT) models have significantly improved 3D point cloud generation. However, existing methods primarily focus on local feature extraction while overlooking global topological information, such as…
We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on…
The emerging trend in computer vision emphasizes developing universal models capable of simultaneously addressing multiple diverse tasks. Such universality typically requires joint training across multi-domain datasets to ensure effective…
Autonomous driving requires 3D maps that provide accurate and up-to-date information about semantic landmarks. Due to the wider availability and lower cost of cameras compared with laser scanners, vision-based mapping solutions, especially…
Point tracking aims to identify the same physical point across video frames and serves as a geometry-aware representation of motion. This representation supports a wide range of applications, from robotics to augmented reality, by enabling…
Layout estimation and 3D object detection are two fundamental tasks in indoor scene understanding. When combined, they enable the creation of a compact yet semantically rich spatial representation of a scene. Existing approaches typically…
We present I2V3D, a novel framework for animating static images into dynamic videos with precise 3D control, leveraging the strengths of both 3D geometry guidance and advanced generative models. Our approach combines the precision of a…
3D dynamic point clouds provide a discrete representation of real-world objects or scenes in motion, which have been widely applied in immersive telepresence, autonomous driving, surveillance, etc. However, point clouds acquired from…
In this paper, we propose a novel 3D registration paradigm, Generative Point Cloud Registration, which bridges advanced 2D generative models with 3D matching tasks to enhance registration performance. Our key idea is to generate cross-view…
Point cloud completion aims to recover partial geometric and topological shapes caused by equipment defects or limited viewpoints. Current methods either solely rely on the 3D coordinates of the point cloud to complete it or incorporate…
3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow.…
In embodied intelligence systems, a key component is 3D perception algorithm, which enables agents to understand their surrounding environments. Previous algorithms primarily rely on point cloud, which, despite offering precise geometric…