English
Related papers

Related papers: DEGround: An Effective Baseline for Ego-centric 3D…

200 papers

Graphical User Interface (GUI) grounding - the task of mapping natural language instructions to screen coordinates - is essential for autonomous agents and accessibility technologies. Existing systems rely on monolithic models or one-shot…

Artificial Intelligence · Computer Science 2025-11-18 SeokJoo Kwak , Jihoon Kim , Boyoun Kim , Jung Jae Yoon , Wooseok Jang , Jeonghoon Hong , Jaeho Yang , Yeong-Dae Kwon

Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references. Despite recent advances, existing methods struggle with reference-target semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Ye Wang , Kai Huang , Sumin Shen , Chenyang Ma

We present ongoing work to harness biological approaches to achieving highly efficient egocentric perception by combining the space-variant imaging architecture of the mammalian retina with Deep Learning methods. By pre-processing images…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Nina Hristozova , Piotr Ozimek , Jan Paul Siebert

Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Gbenga Omotara , Ramy Farag , Seyed Mohamad Ali Tousi , G. N. DeSouza

We present UGround, a \textbf{U}nified visual \textbf{Ground}ing paradigm that dynamically selects intermediate layers across \textbf{U}nrolled transformers as ``mask as prompt,'' diverging from the prevailing pipeline that leverages the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Rui Qian , Xin Yin , Chuanhang Deng , Zhiyuan Peng , Jian Xiong , Wei Zhai , Dejing Dou

Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Yifan Gao , Lu Zou , Zhangjin Huang , Guoping Wang

Visual grounding (VG) tasks involve explicit cross-modal alignment, as semantically corresponding image regions are to be located for the language phrases provided. Existing approaches complete such visual-text reasoning in a single-step…

Computer Vision and Pattern Recognition · Computer Science 2025-02-26 Sijia Chen , Baochun Li

Grounding object properties and relations in 3D scenes is a prerequisite for a wide range of artificial intelligence tasks, such as visually grounded dialogues and embodied manipulation. However, the variability of the 3D domain induces two…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Joy Hsu , Jiayuan Mao , Jiajun Wu

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Mingyue Yang , Yuxin Wen , Weikai Chen , Yongwei Chen , Kui Jia

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Dave Zhenyu Chen , Ronghang Hu , Xinlei Chen , Matthias Nießner , Angel X. Chang

Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Ayush Jain , Alexander Swerdlow , Yuzhou Wang , Sergio Arnaud , Ada Martin , Alexander Sax , Franziska Meier , Katerina Fragkiadaki

Large language models and vision transformers have demonstrated impressive zero-shot capabilities, enabling significant transferability in downstream tasks. The fusion of these models has resulted in multi-modal architectures with enhanced…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Andrés Villa , Juan León Alcázar , Motasem Alfarra , Vladimir Araujo , Alvaro Soto , Bernard Ghanem

We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Kui Wu , Shuhang Xu , Hao Chen , Churan Wang , Zhoujun Li , Yizhou Wang , Fangwei Zhong

Object goal navigation (ObjectNav) in unseen environments is a fundamental task for Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene graphs, or image sequences. Considering this task happens in 3D…

Robotics · Computer Science 2023-04-03 Jiazhao Zhang , Liu Dai , Fanpeng Meng , Qingnan Fan , Xuelin Chen , Kai Xu , He Wang

While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Zehao Li , Wenwei Han , Yujun Cai , Hao Jiang , Baolong Bi , Shuqin Gao , Honglong Zhao , Zhaoqi Wang

Existing Vision Language Models (VLMs) architecturally rooted in "flatland" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conflict between…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Zhongbin Guo , Jiahe Liu , Yushan Li , Wenyu Gao , Zhen Yang , Chenzhi Li , Xinyue Zhang , Ping Jian

This article presents a 3D point cloud map-merging framework for egocentric heterogeneous multi-robot exploration, based on overlap detection and alignment, that is independent of a manual initial guess or prior knowledge of the robots'…

Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks. Unlike end-to-end models that need task-specific data, it advances in performing visual…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Minghe Gao , Juncheng Li , Hao Fei , Liang Pang , Wei Ji , Guoming Wang , Zheqi Lv , Wenqiao Zhang , Siliang Tang , Yueting Zhuang

LiDAR sensors play a crucial role in various applications, especially in autonomous driving. Current research primarily focuses on optimizing perceptual models with point cloud data as input, while the exploration of deeper cognitive…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Yuhang Liu , Boyi Sun , Guixu Zheng , Yishuo Wang , Jing Wang , Fei-Yue Wang

In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with accurate layouts and high fidelity to text descriptions (e.g., spatial relationships), while…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Kai Zou , Hongbo Liu , Dian Zheng , Jianxiong Gao , Zhiwei Zhao , Bin Liu