Zobrazeno 1 - 10
of 527
pro vyhledávání: '"Wu, Tianfu"'
Image-goal navigation enables a robot to reach the location where a target image was captured, using visual cues for guidance. However, current methods either rely heavily on data and computationally expensive learning-based approaches or lack effici
Externí odkaz:
http://arxiv.org/abs/2409.10216
This paper introduces a novel solution to the manual control challenge for indoor blimps. The problem's complexity arises from the conflicting demands of executing human commands while maintaining stability through automatic control for underactuated
Externí odkaz:
http://arxiv.org/abs/2406.10558
Can we localize a robot in radiance fields only using monocular vision? This study presents NuRF, a nudged particle filter framework for 6-DoF robot visual localization in radiance fields. NuRF sets anchors in SE(3) to leverage visual place recogniti
Externí odkaz:
http://arxiv.org/abs/2406.00312
Learning 3D scene representation from a single-view image is a long-standing fundamental problem in computer vision, with the inherent ambiguity in predicting contents unseen from the input view. Built on the recently proposed 3D Gaussian Splatting (
Externí odkaz:
http://arxiv.org/abs/2405.20310
Autor:
Liu, Xianpeng, Zheng, Ce, Qian, Ming, Xue, Nan, Chen, Chen, Zhang, Zhebin, Li, Chen, Wu, Tianfu
We present Multi-View Attentive Contextualization (MvACon), a simple yet effective method for improving 2D-to-3D feature lifting in query-based multi-view 3D (MV3D) object detection. Despite remarkable progress witnessed in the field of query-based M
Externí odkaz:
http://arxiv.org/abs/2405.12200
The adversarial vulnerability of Deep Neural Networks (DNNs) has been well-known and widely concerned, often under the context of learning top-$1$ attacks (e.g., fooling a DNN to classify a cat image as dog). This paper shows that the concern is much
Externí odkaz:
http://arxiv.org/abs/2312.11510
We present Generative Interpretable Fine-Tuning (GIFT) for parameter-efficient fine-tuning of pretrained Transformer backbones, which can be formulated as a simple factorized matrix multiplication in the parameter space or equivalently in the activat
Externí odkaz:
http://arxiv.org/abs/2312.00700
Decision-based black-box attacks often necessitate a large number of queries to craft an adversarial example. Moreover, decision-based attacks based on querying boundary points in the estimated normal vector direction often suffer from inefficiency a
Externí odkaz:
http://arxiv.org/abs/2308.03163
This paper studies the problem of structured 3D reconstruction using wireframes that consist of line segments and junctions, focusing on the computation of structured boundary geometries of scenes. Instead of leveraging matching-based solutions from
Externí odkaz:
http://arxiv.org/abs/2307.10206
The power and flexibility of Optimal Transport (OT) have pervaded a wide spectrum of problems, including recent Machine Learning challenges such as unsupervised domain adaptation. Its essence of quantitatively relating two probability distributions b
Externí odkaz:
http://arxiv.org/abs/2304.08298