Related papers: TrajVG: 3D Trajectory-Coupled Visual Geometry Lear…
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…
Panoramic imagery offers a full 360{\deg} field of view and is increasingly common in consumer devices. However, it introduces non-pinhole distortions that challenge joint pose estimation and 3D reconstruction. Existing feed-forward models,…
Current video generation models produce physically inconsistent motion that violates real-world dynamics. We propose TrajVLM-Gen, a two-stage framework for physics-aware image-to-video generation. First, we employ a Vision Language Model to…
Acquiring 3D geometry of real world objects has various applications in 3D digitization, such as navigation and content generation in virtual environments. Image remains one of the most popular media for such visual tasks due to its…
Photomechanics is a crucial branch of solid mechanics. The localization of point targets constitutes a fundamental problem in optical experimental mechanics, with extensive applications in various missions of UAVs. Localizing moving targets…
3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the…
Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effective multi-view reconstruction in a single forward pass.…
The creation of plausible and controllable 3D human motion animations is a long-standing problem that requires a manual intervention of skilled artists. Current machine learning approaches can semi-automate the process, however, they are…
Recent feed-forward geometry foundation models have demonstrated impressive generalization by recovering depth and poses in a single forward pass. However, these models are typically constrained by a global coordinate frame assumption. This…
We present GTT-Net, a supervised learning framework for the reconstruction of sparse dynamic 3D geometry. We build on a graph-theoretic formulation of the generalized trajectory triangulation problem, where non-concurrent multi-view imaging…
Recent advancements in trajectory-guided video generation have achieved notable progress. However, existing models still face challenges in generating object motions with potentially changing 6D poses under wide-range rotations, due to…
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward framework that simultaneously reconstructs and tracks dynamic video content…
We propose a transformer-based neural network architecture for multi-object 3D reconstruction from RGB videos. It relies on two alternative ways to represent its knowledge: as a global 3D grid of features and an array of view-specific 2D…
We present a method to reconstruct the three-dimensional trajectory of a moving instance of a known object category in monocular video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic…
Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments - humans and different robots - are abundant, differences in embodiment, camera, and…
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…
Feed-forward visual geometry estimation has recently made rapid progress. However, an important gap remains: multi-frame models usually produce better cross-frame consistency, yet they often underperform strong per-frame methods on…
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…
LiDAR-based 3D single object tracking (3D SOT) is a critical task in robotics and autonomous systems. Existing methods typically follow frame-wise motion estimation or a sequence-based paradigm. However, the two-frame methods are efficient…
Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…