Related papers: VGGT: Visual Geometry Grounded Transformer

3D semantic occupancy prediction has become a crucial perception task for comprehensive scene understanding in autonomous driving. While recent advances have explored 3D Gaussian splatting for occupancy modeling to substantially reduce…

We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation and…

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical…

3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics. Existing approaches typically rely on labeled 3D data and…

Human perceive the 3D world through 2D observations from limited viewpoints. While recent feed-forward generalizable 3D reconstruction models excel at recovering 3D structures from sparse images, their representations are often confined to…

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the…

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely on annotated 3D datasets and predefined object…

In autonomous driving, robust place recognition is critical for global localization and loop closure detection. While inter-modality fusion of camera and LiDAR data in multimodal place recognition (MPR) has shown promise in overcoming the…

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,…

End-to-end autonomous driving has evolved from the conventional paradigm based on sparse perception into vision-language-action (VLA) models, which focus on learning language descriptions as an auxiliary task to facilitate planning. In this…

Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper,…

Powerful 3D representations such as DUSt3R invariant point maps, which encode 3D shape and camera parameters, have significantly advanced feed forward 3D reconstruction. While point maps assume static scenes, Dynamic Point Maps (DPMs)…

The drone navigation requires the comprehensive understanding of both visual and geometric information in the 3D world. In this paper, we present a Visual-Geometric Fusion Network(VGF-Net), a deep network for the fusion analysis of…

Existing RGB-based imitation learning approaches typically employ traditional vision encoders such as ResNet or ViT, which lack explicit 3D reasoning capabilities. Recent geometry-grounded vision models, such as VGGT~\cite{wang2025vggt},…

Reconstructing topologically consistent facial geometry is crucial for the digital avatar creation pipelines. Existing methods either require tedious manual efforts, lack generalization to in-the-wild data, or are constrained by the limited…

3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods predominantly operate in the 2D domain, where viewpoint variations are mistaken for…

Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…

In this paper, we introduce 3D-GMNet, a deep neural network for 3D object shape reconstruction from a single image. As the name suggests, 3D-GMNet recovers 3D shape as a Gaussian mixture. In contrast to voxels, point clouds, or meshes, a…

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…