Zobrazeno 1 - 10
of 10 171
pro vyhledávání: '"In Sun Min"'
Autor:
Wilson, Joey, Almeida, Marcelino, Sun, Min, Mahajan, Sachit, Ghaffari, Maani, Ewen, Parker, Ghasemalizadeh, Omid, Kuo, Cheng-Hao, Sen, Arnie
In this paper, we present a novel algorithm for probabilistically updating and rasterizing semantic maps within 3D Gaussian Splatting (3D-GS). Although previous methods have introduced algorithms which learn to rasterize features in 3D-GS for enhance
Externí odkaz:
http://arxiv.org/abs/2411.02547
Autor:
Opipari, Anthony, Krishnan, Aravindhan K, Gayaka, Shreekant, Sun, Min, Kuo, Cheng-Hao, Sen, Arnie, Jenkins, Odest Chadwicke
This paper presents a method for generating large-scale datasets to improve class-agnostic video segmentation across robots with different form factors. Specifically, we consider the question of whether video segmentation models trained on generic se
Externí odkaz:
http://arxiv.org/abs/2410.12995
Autor:
Liang, Jing, Yin, He, Qi, Xuewei, Park, Jong Jin, Sun, Min, Madhivanan, Rajasimman, Manocha, Dinesh
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 estimates for s
Externí odkaz:
http://arxiv.org/abs/2410.11019
Autor:
Basak, Hritam, Tabatabaee, Hadi, Gayaka, Shreekant, Li, Ming-Feng, Yang, Xin, Kuo, Cheng-Hao, Sen, Arnie, Sun, Min, Yin, Zhaozheng
3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Accurately reconstructing an object's complete 3D structure and texture has numerous applica
Externí odkaz:
http://arxiv.org/abs/2410.09467
Pre-explored Semantic Maps, constructed through prior exploration using visual language models (VLMs), have proven effective as foundational elements for training-free robotic applications. However, existing approaches assume the map's accuracy and d
Externí odkaz:
http://arxiv.org/abs/2409.04837
Autor:
Zhang, Ray, Zhou, Zheming, Sun, Min, Ghasemalizadeh, Omid, Kuo, Cheng-Hao, Eustice, Ryan, Ghaffari, Maani, Sen, Arnie
This paper introduces a robust unsupervised SE(3) point cloud registration method that operates without requiring point correspondences. The method frames point clouds as functions in a reproducing kernel Hilbert space (RKHS), leveraging SE(3)-equiva
Externí odkaz:
http://arxiv.org/abs/2407.20223
Autor:
Liang, Jing, Deng, Zhuo, Zhou, Zheming, Sun, Min, Ghasemalizadeh, Omid, Kuo, Cheng-Hao, Sen, Arnie, Manocha, Dinesh
We present a new algorithm, Cross-Source-Context Place Recognition (CSCPR), for RGB-D indoor place recognition that integrates global retrieval and reranking into a single end-to-end model. Unlike prior approaches that primarily focus on the RGB doma
Externí odkaz:
http://arxiv.org/abs/2407.17457
We propose Cooperative Component Analysis (CoCA), a new method for unsupervised multi-view analysis: it identifies the component that simultaneously captures significant within-view variance and exhibits strong cross-view correlation. The challenge o
Externí odkaz:
http://arxiv.org/abs/2407.16870
In this paper, we introduce a novel geometry-aware self-training framework for room layout estimation models on unseen scenes with unlabeled data. Our approach utilizes a ray-casting formulation to aggregate multiple estimates from different viewing
Externí odkaz:
http://arxiv.org/abs/2407.15041
Autor:
Li, Ming-Feng, Ku, Yueh-Feng, Yen, Hong-Xuan, Liu, Chi, Liu, Yu-Lun, Chen, Albert Y. C., Kuo, Cheng-Hao, Sun, Min
Sparse RGBD scene completion is a challenging task especially when considering consistent textures and geometries throughout the entire scene. Different from existing solutions that rely on human-designed text prompts or predefined camera trajectorie
Externí odkaz:
http://arxiv.org/abs/2407.12939