Related papers: Geometric Context Transformer for Streaming 3D Rec…
Traditional SLAM systems, which rely on bundle adjustment, struggle with highly dynamic scenes commonly found in casual videos. Such videos entangle the motion of dynamic elements, undermining the assumption of static environments required…
Sensing the medical scenario can ensure the safety during the surgical operations. So, in this regard, a monitor platform which can obtain the accurate location information of the surgery room is desperately needed. Compared to 2D camera…
Conventional approaches to image-text retrieval mainly focus on indexing visual objects appearing in pictures but ignore the interactions between these objects. Such objects occurrences and interactions are equivalently useful and important…
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult in low-overlap scenarios, showing great potential in…
Online monocular 3D reconstruction enables dense scene recovery from streaming video but remains fundamentally limited by the stability-adaptation dilemma: the reconstruction model must rapidly incorporate novel viewpoints while preserving…
3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…
3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is…
The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offline models like VGGT achieve inspiring geometry capability,…
In the field of resource-constrained robots and the need for effective place recognition in multi-robotic systems, this article introduces RecNet, a novel approach that concurrently addresses both challenges. The core of RecNet's…
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows,…
Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to…
Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial…
In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global…
In recent years, transformer structures have been widely applied in image captioning with impressive performance. For good captioning results, the geometry and position relations of different visual objects are often thought of as crucial…
3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving. Sparse and occluded data in scene point clouds introduce variations in the appearance of tracked…
Visual SLAM algorithms achieve significant improvements through the exploration of 3D Gaussian Splatting (3DGS) representations, particularly in generating high-fidelity dense maps. However, they depend on a static environment assumption…
We present a novel algorithm for estimating the broad 3D geometric structure of outdoor video scenes. Leveraging spatio-temporal video segmentation, we decompose a dynamic scene captured by a video into geometric classes, based on…
We present a latent diffusion model for fast feed-forward 3D scene generation. Given one or more images, our model Bolt3D directly samples a 3D scene representation in less than seven seconds on a single GPU. We achieve this by leveraging…
Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We revisit bounded-memory streaming from the perspective of…
We present a mapping system capable of constructing detailed instance-level semantic models of room-sized indoor environments by means of an RGB-D camera. In this work, we integrate deep-learning-based instance segmentation and…