Related papers: TAPIP3D: Tracking Any Point in Persistent 3D Geome…
Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generalizable 3D world generation. However, existing approaches often…
Cross-category anomaly detection for 3D point clouds aims to determine whether an unseen object belongs to a target category using only a few normal examples. Most existing methods rely on category-specific training, which limits their…
Topological data analysis (TDA) uncovers crucial properties of objects in medical imaging. Methods based on persistent homology have demonstrated their advantages in capturing topological features that traditional deep learning methods…
Recognition of occluded objects in unseen indoor environments is a challenging problem for mobile robots. This work proposes a new slicing-based topological descriptor that captures the 3D shape of object point clouds to address this…
Panoramic video generation aims to synthesize 360-degree immersive videos, holding significant importance in the fields of VR, world models, and spatial intelligence. Existing works fail to synthesize high-quality panoramic videos due to…
Convolutional Neural Networks (CNNs) have emerged as a powerful strategy for most object detection tasks on 2D images. However, their power has not been fully realised for detecting 3D objects in point clouds directly without converting…
Current open-vocabulary scene graph generation algorithms highly rely on both 3D scene point cloud data and posed RGB-D images and thus have limited applications in scenarios where RGB-D images or camera poses are not readily available. To…
This paper presents DeepI2P: a novel approach for cross-modality registration between an image and a point cloud. Given an image (e.g. from a rgb-camera) and a general point cloud (e.g. from a 3D Lidar scanner) captured at different…
Numerous prior studies predominantly emphasize constructing relation vectors for individual neighborhood points and generating dynamic kernels for each vector and embedding these into high-dimensional spaces to capture implicit local…
Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from…
Many existing autonomous driving paradigms involve a multi-stage discrete pipeline of tasks. To better predict the control signals and enhance user safety, an end-to-end approach that benefits from joint spatial-temporal feature learning is…
3D Single Object Tracking (3D-SOT) aims to localize a target object across a sequence of LiDAR point clouds, given its 3D bounding box in the first frame. Recent methods have adopted a memory-based approach to utilize previously observed…
Monocular 3D lane detection is essential for autonomous driving, but challenging due to the inherent lack of explicit spatial information. Multi-modal approaches rely on expensive depth sensors, while methods incorporating fully-supervised…
Event cameras provide microsecond latency, making them suitable for 6D object pose tracking in fast, dynamic scenes where conventional RGB and depth pipelines suffer from motion blur and large pixel displacements. We introduce EventTrack6D,…
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…
In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…
3D Gaussian Splatting techniques have enabled efficient photo-realistic rendering of static scenes. Recent works have extended these approaches to support surface reconstruction and tracking. However, tracking dynamic surfaces with 3D…
Over the past few years, monocular depth estimation and completion have been paid more and more attention from the computer vision community because of their widespread applications. In this paper, we introduce novel physics…
3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveraging the differentiability of the 3DGS renderer "in the wild"…
Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and…