Related papers: Mono-STAR: Mono-camera Scene-level Tracking and Re…
We present a technique for simultaneous 3D reconstruction of static regions and rigidly moving objects in a scene. An RGB-D frame is represented as a collection of features, which are points and planes. We classify the features into static…
The reconstruction and novel view synthesis of dynamic scenes recently gained increased attention. As reconstruction from large-scale multi-view data involves immense memory and computational requirements, recent benchmark datasets provide…
In the intersection of computer vision and robotic perception, 4D reconstruction of dynamic scenes serve as the critical bridge connecting low-level geometric sensing with high-level semantic understanding. We present DINO\_4D, introducing…
In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these…
We present a novel approach for the reconstruction of dynamic geometric shapes using a single hand-held consumer-grade RGB-D sensor at real-time rates. Our method does not require a pre-defined shape template to start with and builds up the…
Current monocular 3D scene reconstruction (3DR) works are either fully-supervised, or not generalizable, or implicit in 3D representation. We propose a novel framework - MonoSelfRecon that for the first time achieves explicit 3D mesh…
Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to…
Recent work has shown impressive localization performance using only images of ground textures taken with a downward facing monocular camera. This provides a reliable navigation method that is robust to feature sparse environments and…
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…
We introduce ET-Former, a novel end-to-end algorithm for semantic scene completion using a single monocular camera. Our approach generates a semantic occupancy map from single RGB observation while simultaneously providing uncertainty…
Camera geo-localization from a monocular video is a fundamental task for video analysis and autonomous navigation. Although 3D reconstruction is a key technique to obtain camera poses, monocular 3D reconstruction in a large environment…
Dynamic 3D reconstruction from monocular videos remains difficult due to the ambiguity inferring 3D motion from limited views and computational demands of modeling temporally varying scenes. While recent sparse control methods alleviate…
In this paper, we present a monocular Simultaneous Localization and Mapping (SLAM) algorithm using high-level object and plane landmarks. The built map is denser, more compact and semantic meaningful compared to feature point based SLAM. We…
Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world scenarios, which encompass adverse weather variations, motion…
Mobile monocular 3D object detection (Mono3D) (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Existing transformer-based offline Mono3D models adopt grid-based vision tokens, which is suboptimal when using…
This paper considers the problem of reconstructing an object with high-resolution using several low-resolution images, which are degraded due to nonuniform defocus effects caused by angular misalignment of the subpixel motions. The new…
Capturing and reconstructing high-speed dynamic 3D scenes has numerous applications in computer graphics, vision, and interdisciplinary fields such as robotics, aerodynamics, and evolutionary biology. However, achieving this using a single…
The development of Text-to-Video (T2V) generation has made motion transfer possible, enabling the control of video motion based on existing footage. However, current methods have two limitations: 1) struggle to handle multi-subjects videos,…
Scene flow estimation is an extremely important task in computer vision to support the perception of dynamic changes in the scene. For robust scene flow, learning-based approaches have recently achieved impressive results using either…
Precisely localizing 3D objects from a single image constitutes a central challenge in monocular 3D detection. While DETR-like architectures offer a powerful paradigm, their direct application in this domain encounters inherent limitations,…