Related papers: Building temporally coherent 3D maps with VGGT for…
We present SceneVGGT, a spatio-temporal 3D scene understanding framework that combines SLAM with semantic mapping for autonomous and assistive navigation. Built on VGGT, our method scales to long video streams via a sliding-window pipeline.…
Current Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating semantic scene knowledge aids in building richer maps with…
We introduce VGGT-SLAM++, a complete visual SLAM system that leverages the geometry-rich outputs of the Visual Geometry Grounded Transformer (VGGT). The system comprises a visual odometry (front-end) fusing the VGGT feed-forward transformer…
Visual Simultaneous Localization and Mapping (vSLAM) is a widely used technique in robotics and computer vision that enables a robot to create a map of an unfamiliar environment using a camera sensor while simultaneously tracking its…
We investigate a challenging task of dynamic scene geometry estimation, which requires representing both spatial and temporal features. Typically, existing methods align the two features into a unified latent space to model scene geometry.…
Recently, the multi-modal fusion of RGB, depth, and semantics has shown great potential in dense Simultaneous Localization and Mapping (SLAM). However, a prerequisite for generating consistent semantic maps is the availability of dense,…
Autonomous robotic systems require spatio-temporal understanding of dynamic environments to ensure reliable navigation and interaction. While Vision-Language Models (VLMs) provide open-world semantic priors, they lack grounding in 3D…
Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when…
Simultaneous Localization and Mapping (SLAM) plays an important role in many robotics fields, including social robots. Many of the available visual SLAM methods are based on the assumption of a static world and struggle in dynamic…
Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic environments and enable open-vocabulary querying in complex…
Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed-forward 3D models have demonstrated strong performance in…
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a…
Integrating open-vocabulary semantic information into dynamic 3D scene representations is essential for long-term embodied scene understanding. However, existing methods often suffer from fragile instance association due to incomplete…
3D occupancy prediction is critical for comprehensive scene understanding in vision-centric autonomous driving. Recent advances have explored utilizing 3D semantic Gaussians to model occupancy while reducing computational overhead, but they…
3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce…
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…
3D Gaussian Splatting (3DGS) has shown promising results for 3D scene modeling using mixtures of Gaussians, yet its existing simultaneous localization and mapping (SLAM) variants typically rely on direct, deterministic pose optimization…
Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar…
Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs.…
The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass.…