相关论文: MoRe: Monocular Geometry Refinement via Graph Opti…

High-fidelity 3D scene reconstruction from monocular videos continues to be challenging, especially for complete and fine-grained geometry reconstruction. The previous 3D reconstruction approaches with neural implicit representations have…

Rendering realistic images from 3D reconstruction is an essential task of many Computer Vision and Robotics pipelines, notably for mixed-reality applications as well as training autonomous agents in simulated environments. However, the…

We present a novel monocular localization framework by jointly training deep learning-based depth prediction and Bayesian filtering-based pose reasoning. The proposed cross-modal framework significantly outperforms deep learning-only…

Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor…

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…

This paper investigates the geometric consistency for monocular 3D object detection, which suffers from the ill-posed depth estimation. We first conduct a thorough analysis to reveal how existing methods fail to consistently localize…

Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-posed face pose and depth ambiguity issue. In contrast to…

Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applicability of SLAM…

We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets…

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video.…

Although the majority of recent autonomous driving systems concentrate on developing perception methods based on ego-vehicle sensors, there is an overlooked alternative approach that involves leveraging intelligent roadside cameras to help…

Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually plausible reconstructions often contain errors, particularly…

3D face alignment is a very challenging and fundamental problem in computer vision. Existing deep learning-based methods manually design different networks to regress either parameters of a 3D face model or 3D positions of face vertices.…

Monocular depth priors have been widely adopted by neural rendering in multi-view based tasks such as 3D reconstruction and novel view synthesis. However, due to the inconsistent prediction on each view, how to more effectively leverage…

In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to directly predict absolute depth, recent advancements advocate…

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose…

This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture. We ease the learning process by obtaining coarse camera poses from monocular sequences…

3D pose estimation from sparse multi-views is a critical task for numerous applications, including action recognition, sports analysis, and human-robot interaction. Optimization-based methods typically follow a two-stage pipeline, first…

We address the problems of measuring geometric similarity between 3D scenes, represented through point clouds or range data frames, and associating them. Our approach leverages macro-scale 3D structural geometry - the relative configuration…

Accurate surround-view depth estimation provides a competitive alternative to laser-based sensors and is essential for 3D scene understanding in autonomous driving. While empirical studies have proposed various approaches that primarily…