Related papers: VoxDepth: Rectification of Depth Images on Edge De…
Depth information is useful for many applications. Active depth sensors are appealing because they obtain dense and accurate depth maps. However, due to issues that range from power constraints to multi-sensor interference, these sensors…
Accurate 6D object pose estimation is a prerequisite for successfully completing robotic prehensile and non-prehensile manipulation tasks. At present, 6D pose estimation for robotic manipulation generally relies on depth sensors based on,…
Video stabilization aims to mitigate camera shake but faces a fundamental trade-off between geometric robustness and full-frame consistency. While 2D methods suffer from aggressive cropping, 3D techniques are often undermined by fragile…
The 3D reconstruction of simultaneous localization and mapping (SLAM) is an important topic in the field for transport systems such as drones, service robots and mobile AR/VR devices. Compared to a point cloud representation, the 3D…
360-degree images offer a significantly wider field of view compared to traditional pinhole cameras, enabling sparse sampling and dense 3D reconstruction in low-texture environments. This makes them crucial for applications in VR, AR, and…
Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving. This study proposes a comprehensive self-supervised framework for accurate scale-aware depth prediction on autonomous…
Learning depth from a single image, as an important issue in scene understanding, has attracted a lot of attention in the past decade. The accuracy of the depth estimation has been improved from conditional Markov random fields,…
Monocular Depth Estimation (MDE) enables spatial understanding, 3D reconstruction, and autonomous navigation, yet deep learning approaches often predict only relative depth without a consistent metric scale. This limitation reduces…
We introduce Metric3D v2, a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image, which is crucial for metric 3D recovery. While depth and normal are geometrically related and highly…
Synthesizing accurate geometry and photo-realistic appearance of small scenes is an active area of research with compelling use cases in gaming, virtual reality, robotic-manipulation, autonomous driving, convenient product capture, and…
Bokeh rendering and depth estimation share a fundamental optical connection, yet existing methods fail to fully exploit this reciprocity. Conventional bokeh pipelines rely heavily on noisy depth maps that inevitably introduce visual…
Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in terms of evaluation metrics such as the pixel-wise relative error, most methods neglect the…
Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous driving and robotics. Compared to the complex, multi-modal systems deployed today, multi-camera systems provide a simpler, low-cost alternative. However,…
Depth estimation is a crucial step for image-guided intervention in robotic surgery and laparoscopic imaging system. Since per-pixel depth ground truth is difficult to acquire for laparoscopic image data, it is rarely possible to apply…
Image editing and compositing have become ubiquitous in entertainment, from digital art to AR and VR experiences. To produce beautiful composites, the camera needs to be geometrically calibrated, which can be tedious and requires a physical…
Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR technologies. Traditional methods relying on hardware…
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…
Dense reconstructions often contain errors that prior work has so far minimised using high quality sensors and regularising the output. Nevertheless, errors still persist. This paper proposes a machine learning technique to identify errors…
Depth maps produced by consumer-grade sensors suffer from inaccurate measurements and missing data from either system or scene-specific sources. Data-driven denoising algorithms can mitigate such problems. However, they require vast amounts…
Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training…