Related papers: VGGT-CD: Training-Free Robust Registration for 3D …
Maintaining an up-to-date map that accurately reflects recent changes in the environment is crucial, especially for robots that repeatedly traverse the same space. Failing to promptly update the changed regions can degrade map quality,…
3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness critically depends on the quality of the initialized point cloud. Specifically, achieving uniform…
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,…
Remote sensing change detection (CD) aims to identify where land-cover semantics change across time, but most existing methods still assume a fixed label space and therefore cannot answer arbitrary user-defined queries. Open-vocabulary…
Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks. Here, we show that the quality of these…
Partial point cloud registration is essential for autonomous perception and 3D scene understanding, yet it remains challenging owing to structural ambiguity, partial visibility, and noise. We address these issues by proposing Confidence…
Target localization is a prerequisite for embodied tasks such as navigation and manipulation. Conventional approaches rely on constructing explicit 3D scene representations to enable target localization, such as point clouds, voxel grids,…
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.…
Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing $O(1)$ frameworks primarily rely on a ``pure eviction'' paradigm, which suffers from significant information…
3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a…
The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description. We propose, 2D3D-MATR, a detection-free method…
Visual Geometry Grounded Transformer (VGGT) advances 3D reconstruction via scalable Transformer architecture, but the quadratic complexity of global attention prevents long context application. StreamVGGT enables streaming with causal…
State-of-the-art 3D computer vision algorithms continue to advance in handling sparse, unordered image sets. Recently developed foundational models for 3D reconstruction, such as Dense and Unconstrained Stereo 3D Reconstruction (DUSt3R),…
High-fidelity 3D reconstruction of vehicle exteriors improves buyer confidence in online automotive marketplaces, but generating these models in cluttered dealership drive-throughs presents severe technical challenges. Unlike static-scene…
Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…
In the conventional change detection (CD) pipeline, two manually registered and labeled remote sensing datasets serve as the input of the model for training and prediction. However, in realistic scenarios, data from different periods or…
Reconstructing dynamic scenes from Vehicle-to-Infrastructure Cooperative Autonomous Driving (VICAD) data is fundamentally complicated by temporal asynchrony: vehicle and infrastructure cameras operate on independent clocks, capturing the…
Change detection (CD) in remote sensing is vital for applications such as urban monitoring and disaster assessment, yet traditional methods struggle with generalization across diverse scenarios. We present OmniCD, a foundational framework…
Accurate 3D reconstruction of deformable soft tissues is essential for surgical robotic perception. However, low-texture surfaces, specular highlights, and instrument occlusions often fragment geometric continuity, posing a challenge for…