English
Related papers

Related papers: Geometry-Aware Rotary Position Embedding for Consi…

200 papers

Video generation with controllable camera viewpoints is essential for applications such as interactive content creation, gaming, and simulation. Existing methods typically adapt pre-trained video models using camera poses relative to a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Chunyang Li , Yuanbo Yang , Jiahao Shao , Hongyu Zhou , Katja Schwarz , Yiyi Liao

Relative position embedding has become a standard mechanism for encoding positional information in Transformers. However, existing formulations are typically limited to a fixed geometric space, namely 1D sequences or regular 2D/3D grids,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Yichen Xie , Depu Meng , Chensheng Peng , Yihan Hu , Quentin Herau , Masayoshi Tomizuka , Wei Zhan

We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows $SE(3)$-invariant attention with multi-frequency similarity, and can…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Yu Wu , Minsik Jeon , Jen-Hao Rick Chang , Oncel Tuzel , Shubham Tulsiani

World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating complex physical interactions. However, existing interactive…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Junyi Chen , Haoyi Zhu , Xianglong He , Yifan Wang , Jianjun Zhou , Wenzheng Chang , Yang Zhou , Zizun Li , Zhoujie Fu , Jiangmiao Pang , Tong He

Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations,…

Artificial Intelligence · Computer Science 2025-11-03 Zikang Liu , Longteng Guo , Yepeng Tang , Tongtian Yue , Junxian Cai , Kai Ma , Qingbin Liu , Xi Chen , Jing Liu

Standard Vision Transformers flatten 2D images into 1D sequences, disrupting the natural spatial topology. While Rotary Positional Embedding (RoPE) excels in 1D, it inherits this limitation, often treating spatially distant patches (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Yupu Yao , Bowen Yang

Recent advances in diffusion-based generation techniques enable AI models to produce highly realistic videos, heightening the need for reliable detection mechanisms. However, existing detection methods provide only limited exploration of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Wenhan Chen , Sezer Karaoglu , Theo Gevers

While Rotary Position Embedding (RoPE) and its variants are widely adopted for their long-context capabilities, the extension of the 1D RoPE to video, with its complex spatio-temporal structure, remains an open challenge. This work first…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Xilin Wei , Xiaoran Liu , Yuhang Zang , Xiaoyi Dong , Pan Zhang , Yuhang Cao , Jian Tong , Haodong Duan , Qipeng Guo , Jiaqi Wang , Xipeng Qiu , Dahua Lin

Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other…

Graphics · Computer Science 2025-04-02 Tian-Xing Xu , Xiangjun Gao , Wenbo Hu , Xiaoyu Li , Song-Hai Zhang , Ying Shan

Video depth estimation extends monocular prediction into the temporal domain to ensure coherence. However, existing methods often suffer from spatial blurring in fine-detail regions and temporal inconsistencies. We argue that current…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Yuecheng Liu , Junda Cheng , Longliang Liu , Wenjing Liao , Hanrui Cheng , Yuzhou Wang , Xin Yang

Vision foundation models (VFMs) and Bird's Eye View (BEV) representation have advanced visual perception substantially, yet their internal spatial representations assume the rectilinear geometry of pinhole cameras. Fisheye cameras, widely…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Rahul Ahuja , Mudit Jain , Bala Murali Manoghar Sai Sudhakar , Venkatraman Narayanan , Pratik Likhar , Varun Ravi Kumar , Senthil Yogamani

Transformers rely on explicit positional encoding to model structure in data. While Rotary Position Embedding (RoPE) excels in 1D domains, its application to image generation reveals significant limitations such as fine-grained spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Jiaye Li , Baoyou Chen , Hui Li , Zilong Dong , Jingdong Wang , Siyu Zhu

In this paper we propose a geometry-aware model for video object detection. Specifically, we consider the setting that cameras can be well approximated as static, e.g. in video surveillance scenarios, and scene pseudo depth maps can…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Dan Xu , Weidi Xie , Andrew Zisserman

Multi-camera 3D object detection for autonomous driving is a challenging problem that has garnered notable attention from both academia and industry. An obstacle encountered in vision-based techniques involves the precise extraction of…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Linyan Huang , Huijie Wang , Jia Zeng , Shengchuan Zhang , Liujuan Cao , Junchi Yan , Hongyang Li

Positional encoding is a vital component of Transformer architectures, enabling models to incorporate sequence order into self-attention mechanisms. Rotary Positional Embeddings (RoPE) have become a widely adopted solution due to their…

Computation and Language · Computer Science 2025-08-01 Ali Veisi , Delaram Fartoot , Hamidreza Amirzadeh

Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Zeyi Liu , Shuang Li , Eric Cousineau , Siyuan Feng , Benjamin Burchfiel , Shuran Song

Recent advancements in world models have revolutionized dynamic environment simulation, allowing systems to foresee future states and assess potential actions. In autonomous driving, these capabilities help vehicles anticipate the behavior…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Anthony Chen , Wenzhao Zheng , Yida Wang , Xueyang Zhang , Kun Zhan , Peng Jia , Kurt Keutzer , Shanghang Zhang

Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct…

Robotics · Computer Science 2025-03-20 Jianbo Zhao , Taiyu Ban , Zhihao Liu , Hangning Zhou , Xiyang Wang , Qibin Zhou , Hailong Qin , Mu Yang , Lei Liu , Bin Li

Virtual tour among sparse 360$^\circ$ images is widely used while hindering smooth and immersive roaming experiences. The emergence of Neural Radiance Field (NeRF) has showcased significant progress in synthesizing novel views, unlocking…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Huajian Huang , Yingshu Chen , Tianjia Zhang , Sai-Kit Yeung

Spatial reasoning focuses on locating target objects based on spatial relations in 3D scenes, which plays a crucial role in developing intelligent embodied agents. Due to the limited availability of 3D scene-language paired data, it is…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Shengli Zhou , Minghang Zheng , Feng Zheng , Yang Liu
‹ Prev 1 2 3 10 Next ›