中文
相关论文

相关论文: Stronger, Steadier & Superior: Geometric Consisten…

200 篇论文

Real-world weather, illumination, and imaging variations often induce severe domain shifts, degrading single-source detectors in unseen environments. Existing single-domain generalized object detection (SDGOD) methods mainly rely on data…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Yupeng Zhang , Ruize Han , Ningnan Guo , Wei Feng , Song Wang , Liang Wan

In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Zhixiang Wei , Lin Chen , Yi Jin , Xiaoxiao Ma , Tianle Liu , Pengyang Ling , Ben Wang , Huaian Chen , Jinjin Zheng

Domain Generalized Semantic Segmentation (DGSS) aims to improve the generalization ability of models across unseen domains without access to target data during training. Recent advances in DGSS have increasingly exploited vision foundation…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Xinhui Li , Xiaojie Guo

The rapid development of Vision Foundation Model (VFM) brings inherent out-domain generalization for a variety of down-stream tasks. Among them, domain generalized semantic segmentation (DGSS) holds unique challenges as the cross-domain…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Jingjun Yi , Qi Bi , Hao Zheng , Haolan Zhan , Wei Ji , Yawen Huang , Yuexiang Li , Yefeng Zheng

The demand for high-resolution subsurface imaging and continuous Earth monitoring has driven rapid growth in active and passive seismic data from dense geophone deployments, distributed acoustic sensing (DAS) arrays, and large-scale 2D and…

地球物理 · 物理学 2026-05-13 Jiahua Zhao , Umair bin Waheed , Jing Sun , Yang Cui , Nikos Savva , Eric Verschuur

In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Anlin Zheng , Qi Han , Xin Wen , Chuofan Ma , Lanxi Gong , Gang Yu , Xiangyu Zhang , Xiaojuan Qi

Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Yachan Guo , JoseLuis Gomez Zurita , Danna Xue , Yi Xiao , AntonioManuel Lopez Pena

Open-Vocabulary semantic segmentation (OVSS) and domain generalization in semantic segmentation (DGSS) highlight a subtle complementarity that motivates Open-Vocabulary Domain-Generalized Semantic Segmentation (OV-DGSS). OV-DGSS aims to…

计算机视觉与模式识别 · 计算机科学 2025-12-12 Siyu Chen , Ting Han , Chengzheng Fu , Changshe Zhang , Chaolei Wang , Jinhe Su , Guorong Cai , Meiliu Wu

Recent Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) such as CLIP exhibit strong generalization capabilities in detecting artifacts across different identities. However, existing…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Jiawen Zhu , Yunqi Miao , Xueyi Zhang , Jiankang Deng , Guansong Pang

Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple…

计算机视觉与模式识别 · 计算机科学 2025-09-08 Tianpei Zhang , Jufeng Zhao , Yiming Zhu , Guangmang Cui

Recent domain generalized semantic segmentation (DGSS) studies have achieved notable improvements by distilling semantic knowledge from Vision-Language Models (VLMs). However, they overlook the semantic misalignment between visual and…

计算机视觉与模式识别 · 计算机科学 2025-12-19 Seogkyu Jeon , Kibeom Hong , Hyeran Byun

Vision foundation models (VFMs) have emerged as powerful tools for surgical scene understanding. However, current approaches predominantly rely on unimodal RGB pre-training, overlooking the complex 3D geometry inherent to surgical…

计算机视觉与模式识别 · 计算机科学 2026-01-28 John J. Han , Adam Schmidt , Muhammad Abdullah Jamal , Chinedu Nwoye , Anita Rau , Jie Ying Wu , Omid Mohareri

Structure-from-motion (SfM) is a long-standing problem in the computer vision community, which aims to reconstruct the camera poses and 3D structure of a scene from a set of unconstrained 2D images. Classical frameworks solve this problem…

计算机视觉与模式识别 · 计算机科学 2023-12-08 Jianyuan Wang , Nikita Karaev , Christian Rupprecht , David Novotny

Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer vision. Existing approaches suffer from two limitations: (i) Geometric Ambiguity: Their…

计算机视觉与模式识别 · 计算机科学 2025-09-26 Songlin Yang , Tianyi Wei , Yushi Lan , Zeqi Xiao , Anyi Rao , Xingang Pan

We introduce a learning-based depth map fusion framework that accepts a set of depth and confidence maps generated by a Multi-View Stereo (MVS) algorithm as input and improves them. This is accomplished by integrating volumetric visibility…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Nathaniel Burgdorfer , Philippos Mordohai

The reliable computational assessment of photographic composition requires features that are discriminative of spatial layout yet robust to semantic content. This paper proposes a low-level representation grounded in the assumption that…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Armin Dadras , Robert Sablatnig , Franziska Proksa , Markus Seidl

Vision Foundation Models (VFMs) excel in generalization due to large-scale pretraining, but fine-tuning them for Domain Generalized Semantic Segmentation (DGSS) while maintaining this ability remains challenging. Existing approaches either…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Dong Zhao , Jinlong Li , Shuang Wang , Mengyao Wu , Qi Zang , Nicu Sebe , Zhun Zhong

Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies issues further, hindering multi-dataset training and zero-shot…

计算机视觉与模式识别 · 计算机科学 2025-09-26 Karlo Koledić , Luka Petrović , Ivan Marković , Ivan Petrović

Domain generalization (DG) aims to maintain performance under domain shift, which in computer vision appears primarily as stylistic variations that cause models to overfit to domain-specific appearance cues rather than class semantics. To…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Antonios Kritikos , Nikolaos Spanos , Athanasios Voulodimos

Semantic segmentation networks trained under full supervision for one type of lidar fail to generalize to unseen lidars without intervention. To reduce the performance gap under domain shifts, a recent trend is to leverage vision foundation…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Björn Michele , Alexandre Boulch , Gilles Puy , Tuan-Hung Vu , Renaud Marlet , Nicolas Courty
‹ 上一页 1 2 3 10 下一页 ›