Related papers: LongDPM: Overlap-Aware 4D Reconstruction from Long…
Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D…
Recovering 4D from monocular video, which jointly estimates dynamic geometry and camera poses, is an inevitably challenging problem. While recent pointmap-based 3D reconstruction methods (e.g., DUSt3R) have made great progress in…
Advances in Deep Learning have recently made it possible to recover full 3D meshes of human poses from individual images. However, extension of this notion to videos for recovering temporally coherent poses still remains unexplored. A major…
Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but they fundamentally suffer from a Memory Demand Dilemma: The…
In monocular videos that capture dynamic scenes, estimating the 3D geometry of video contents has been a fundamental challenge in computer vision. Specifically, the task is significantly challenged by the object motion, where existing…
With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to…
Existing monocular depth estimation methods have achieved excellent robustness in diverse scenes, but they can only retrieve affine-invariant depth, up to an unknown scale and shift. However, in some video-based scenarios such as video…
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)…
Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…
We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panoptic Studio). Such multi-view setups are prohibitively…
This paper proposes a new approach for monocular dense 3D reconstruction of a complex dynamic scene from two perspective frames. By applying superpixel over-segmentation to the image, we model a generically dynamic (hence non-rigid) scene…
Video understanding in multimodal large language models requires selecting informative frames from long, redundant videos under limited visual-token budgets. Existing methods often rely on uniform sampling, point-wise relevance scoring,…
While the keypoint-based maps created by sparse monocular simultaneous localisation and mapping (SLAM) systems are useful for camera tracking, dense 3D reconstructions may be desired for many robotic tasks. Solutions involving depth cameras…
Real-time 3D reconstruction enables fast dense mapping of the environment which benefits numerous applications, such as navigation or live evaluation of an emergency. In contrast to most real-time capable approaches, our approach does not…
The choice of data representation is a key factor in the success of deep learning in geometric tasks. For instance, DUSt3R recently introduced the concept of viewpoint-invariant point maps, generalizing depth prediction and showing that all…
Monocular depth reconstruction of complex and dynamic scenes is a highly challenging problem. While for rigid scenes learning-based methods have been offering promising results even in unsupervised cases, there exists little to no…
DUSt3R has recently shown that one can reduce many tasks in multi-view geometry, including estimating camera intrinsics and extrinsics, reconstructing the scene in 3D, and establishing image correspondences, to the prediction of a pair of…
This paper is on long-term video understanding where the goal is to recognise human actions over long temporal windows (up to minutes long). In prior work, long temporal context is captured by constructing a long-term memory bank consisting…
Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…
In this paper, we propose a dense monocular SLAM system, named DeepRelativeFusion, that is capable to recover a globally consistent 3D structure. To this end, we use a visual SLAM algorithm to reliably recover the camera poses and…