Related papers: MonoMobility: Zero-Shot 3D Mobility Analysis from …
3D scene understanding is a long-standing challenge in computer vision and a key component in enabling mixed reality, wearable computing, and embodied AI. Providing a solution to these applications requires a multifaceted approach that…
Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real…
An object's interior material properties, while invisible to the human eye, determine motion observed on its surface. We propose an approach that estimates heterogeneous material properties of an object from a monocular video of its surface…
Recovering world-coordinate human motion from monocular videos with humanoid robot retargeting is significant for embodied intelligence and robotics. To avoid complex SLAM pipelines or heavy temporal models, we propose a lightweight,…
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…
Our goal in this work is to generate realistic videos given just one initial frame as input. Existing unsupervised approaches to this task do not consider the fact that a video typically shows a 3D environment, and that this should remain…
We propose a method for in-hand 3D scanning of an unknown object with a monocular camera. Our method relies on a neural implicit surface representation that captures both the geometry and the appearance of the object, however, by contrast…
We present MoBGS, a novel motion deblurring 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner. Existing dynamic novel…
We introduce D3D-HOI: a dataset of monocular videos with ground truth annotations of 3D object pose, shape and part motion during human-object interactions. Our dataset consists of several common articulated objects captured from diverse…
We introduce an approach for detecting and tracking detailed 3D poses of multiple people from a single monocular camera stream. Our system maintains temporally coherent predictions in crowded scenes filled with difficult poses and…
Modeling and rendering dynamic urban driving scenes is crucial for self-driving simulation. Current high-quality methods typically rely on costly manual object tracklet annotations, while self-supervised approaches fail to capture dynamic…
Realistic scene reconstruction in driving scenarios poses significant challenges due to fast-moving objects. Most existing methods rely on labor-intensive manual labeling of object poses to reconstruct dynamic objects in canonical space and…
Most SLAM algorithms are based on the assumption that the scene is static. However, in practice, most scenes are dynamic which usually contains moving objects, these methods are not suitable. In this paper, we introduce DymSLAM, a dynamic…
With the rapid development of deep learning algorithms, action recognition in video has achieved many important research results. One issue in action recognition, Zero-Shot Action Recognition (ZSAR), has recently attracted considerable…
Can we learn robot manipulation for everyday tasks, only by watching videos of humans doing arbitrary tasks in different unstructured settings? Unlike widely adopted strategies of learning task-specific behaviors or direct imitation of a…
3D Gaussian Splatting (3DGS) has become an emerging tool for dynamic scene reconstruction. However, existing methods focus mainly on extending static 3DGS into a time-variant representation, while overlooking the rich motion information…
Gaussian splatting has become a popular representation for novel-view synthesis, exhibiting clear strengths in efficiency, photometric quality, and compositional edibility. Following its success, many works have extended Gaussians to 4D,…
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…
Recent geometric methods need reliable estimates of 3D motion parameters to procure accurate dense depth map of a complex dynamic scene from monocular images \cite{kumar2017monocular, ranftl2016dense}. Generally, to estimate…
Reconstructing structured 3D scenes from RGB images using CAD objects unlocks efficient and compact scene representations that maintain compositionality and interactability. Existing works propose training-heavy methods relying on either…