中文
相关论文

相关论文: XDen-1K: A Density Field Dataset of Real-World Obj…

200 篇论文

Limited real-world data severely impacts model performance in many computer vision domains, particularly for samples that are underrepresented in training. Synthetically generated images are a promising solution, but 1) it remains unclear…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Nitish Mital , Simon Malzard , Richard Walters , Celso M. De Melo , Raghuveer Rao , Victoria Nockles

Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mainstream research in 3D vision has primarily focused on manipulation through depth perception…

机器人学 · 计算机科学 2025-03-24 Wenbo Cui , Chengyang Zhao , Songlin Wei , Jiazhao Zhang , Haoran Geng , Yaran Chen , Haoran Li , He Wang

Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments. However, existing methods that leverage differentiable…

机器人学 · 计算机科学 2025-05-13 Yifan Zhu , Tianyi Xiang , Aaron Dollar , Zherong Pan

3D Gaussian Splatting (3DGS) has emerged as a promising approach for novel view synthesis, offering real-time rendering with high visual fidelity. However, its substantial storage requirements present significant challenges for practical…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Yuke Xing , Jiarui Wang , Peizhi Niu , Wenjie Huang , Guangtao Zhai , Yiling Xu

Imitation learning is a prominent paradigm for robotic manipulation. However, existing visual imitation methods map 2D image observations directly to 3D action outputs, imposing a 2D-3D mismatch that hinders spatial reasoning and degrades…

机器人学 · 计算机科学 2026-03-19 Tianxing Zhou , Feiyang Xue , Zhangchen Ye , Tianyuan Yuan , Hang Zhao , Tao Jiang

Recently deep residual learning with residual units for training very deep neural networks advanced the state-of-the-art performance on 2D image recognition tasks, e.g., object detection and segmentation. However, how to fully leverage…

计算机视觉与模式识别 · 计算机科学 2016-08-23 Hao Chen , Qi Dou , Lequan Yu , Pheng-Ann Heng

In this work, we present a dense tracking and mapping system named Vox-Fusion, which seamlessly fuses neural implicit representations with traditional volumetric fusion methods. Our approach is inspired by the recently developed implicit…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Xingrui Yang , Hai Li , Hongjia Zhai , Yuhang Ming , Yuqian Liu , Guofeng Zhang

We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured…

Accurately estimating the shape of objects in dense clutters makes important contribution to robotic packing, because the optimal object arrangement requires the robot planner to acquire shape information of all existed objects. However,…

机器人学 · 计算机科学 2023-02-24 Zhenyu Wu , Ziwei Wang , Jiwen Lu , Haibin Yan

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities across various multimodal tasks. They continue, however, to struggle with trivial scenarios such as reading values from Digital…

计算机视觉与模式识别 · 计算机科学 2025-09-01 João Valente , Atabak Dehban , Rodrigo Ventura

Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i.e., localization, dimension, and orientation. Despite its popularity and universality, such a straightforward…

计算机视觉与模式识别 · 计算机科学 2022-04-01 Xuelin Qian , Li Wang , Yi Zhu , Li Zhang , Yanwei Fu , Xiangyang Xue

We propose SiM3D, the first benchmark considering the integration of multiview and multimodal information for comprehensive 3D anomaly detection and segmentation (ADS), where the task is to produce a voxel-based Anomaly Volume. Moreover,…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Alex Costanzino , Pierluigi Zama Ramirez , Luigi Lella , Matteo Ragaglia , Alessandro Oliva , Giuseppe Lisanti , Luigi Di Stefano

Understanding objects through multiple sensory modalities is fundamental to human perception, enabling cross-sensory integration and richer comprehension. For AI and robotic systems to replicate this ability, access to diverse, high-quality…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Samuel Clarke , Suzannah Wistreich , Yanjie Ze , Jiajun Wu

We consider the problem of enriching current object detection systems with veridical object sizes and relative depth estimates from a single image. There are several technical challenges to this, such as occlusions, lack of calibration data…

计算机视觉与模式识别 · 计算机科学 2015-10-02 Abhishek Kar , Shubham Tulsiani , João Carreira , Jitendra Malik

The way an object looks and sounds provide complementary reflections of its physical properties. In many settings cues from vision and audition arrive asynchronously but must be integrated, as when we hear an object dropped on the floor and…

计算机视觉与模式识别 · 计算机科学 2022-07-08 Chuang Gan , Yi Gu , Siyuan Zhou , Jeremy Schwartz , Seth Alter , James Traer , Dan Gutfreund , Joshua B. Tenenbaum , Josh McDermott , Antonio Torralba

To be useful in everyday environments, robots must be able to observe and learn about objects. Recent datasets enable progress for classifying data into known object categories; however, it is unclear how to collect reliable object data…

机器人学 · 计算机科学 2019-01-18 Abhishek Venkataraman , Brent Griffin , Jason J. Corso

Dense pixel-specific representation learning at scale has been bottlenecked due to the unavailability of large-scale multi-view datasets. Current methods for building effective pretraining datasets heavily rely on annotated 3D meshes, point…

The development of modern Artificial Intelligence (AI) models, particularly diffusion-based models employed in computer vision and image generation tasks, is undergoing a paradigmatic shift in development methodologies. Traditionally…

机器学习 · 计算机科学 2025-06-13 Sajjad Abdoli , Freeman Lewin , Gediminas Vasiliauskas , Fabian Schonholz

While 3D object bounding box (bbox) representation has been widely used in autonomous driving perception, it lacks the ability to capture the precise details of an object's intrinsic geometry. Recently, occupancy has emerged as a promising…

计算机视觉与模式识别 · 计算机科学 2024-12-09 Chaoda Zheng , Feng Wang , Naiyan Wang , Shuguang Cui , Zhen Li

We focus on the task of amodal 3D object detection in RGB-D images, which aims to produce a 3D bounding box of an object in metric form at its full extent. We introduce Deep Sliding Shapes, a 3D ConvNet formulation that takes a 3D…

计算机视觉与模式识别 · 计算机科学 2016-03-10 Shuran Song , Jianxiong Xiao
‹ 上一页 1 8 9 10 下一页 ›