相关论文: Analytical Derivatives for Differentiable Renderer…

Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research. Nevertheless, assuming a multiple-view system composed of several regular RGB cameras, 3D multi-pose estimation presents several…

Despite the fact that object detection, 3D pose estimation, and sub-category recognition are highly correlated tasks, they are usually addressed independently from each other because of the huge space of parameters. To jointly model all of…

3D pose estimation from a single image is a challenging task in computer vision. We present a weakly supervised approach to estimate 3D pose points, given only 2D pose landmarks. Our method does not require correspondences between 2D and 3D…

3D object detection and pose estimation from a single image are two inherently ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to shape symmetries, occlusion and repetitive textures. This ambiguity in…

Capturing the 3D geometry of transparent objects is a challenging task, ill-suited for general-purpose scanning and reconstruction techniques, since these cannot handle specular light transport phenomena. Existing state-of-the-art methods,…

Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object in an RGB-D image which is the topic of this work. The idea is to compare the observation with the output of a…

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus…

In real-time rendering, a 3D scene is modelled with meshes of triangles that the GPU projects to the screen. They are discretized by sampling each triangle at regular space intervals to generate fragments which are then added texture and…

Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set. An inaccurate estimation may mislead the model into learning faulty geometry. This work proposes PoF3D that frees…

Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome…

Differentiable rendering with 3D Gaussian primitives has emerged as a powerful method for reconstructing high-fidelity 3D scenes from multi-view images. While it offers improvements over NeRF-based methods, this representation still…

In the context of future manufacturing lines, removing fixtures will be a fundamental step to increase the flexibility of autonomous systems in assembly and logistic operations. Vision-based 3D pose estimation is a necessity to accurately…

Although Neural Differential Equations have shown promise on toy problems such as MNIST, they have yet to be successfully applied to more challenging tasks. Inspired by variational methods for image restoration relying on partial…

Since the introduction of modern deep learning methods for object pose estimation, test accuracy and efficiency has increased significantly. For training, however, large amounts of annotated training data are required for good performance.…

Ultrasound (US) image segmentation embraced its significant improvement in deep learning era. However, the lack of sharp boundaries in US images still remains an inherent challenge for segmentation. Previous methods often resort to global…

Line segments are ubiquitous in our human-made world and are increasingly used in vision tasks. They are complementary to feature points thanks to their spatial extent and the structural information they provide. Traditional line detectors…

This paper presents a framework that combines traditional keypoint-based camera pose optimization with an invertible neural rendering mechanism. Our proposed 3D scene representation, Nerfels, is locally dense yet globally sparse. As opposed…

Due to the limited model capacity, leveraging distributed Neural Radiance Fields (NeRFs) for modeling extensive urban environments has become a necessity. However, current distributed NeRF registration approaches encounter aliasing…

Multi-view image-based rendering consists in generating a novel view of a scene from a set of source views. In general, this works by first doing a coarse 3D reconstruction of the scene, and then using this reconstruction to establish…

Automated 3D pose estimation of satellites and other known space objects is a critical component of space situational awareness. Ground-based imagery offers a convenient data source for satellite characterization; however, analysis…