English
Related papers

Related papers: ORV: 4D Occupancy-centric Robot Video Generation

200 papers

Multi-view image generation in autonomous driving demands consistent 3D scene understanding across camera views. Most existing methods treat this problem as a 2D image set generation task, lacking explicit 3D modeling. However, we argue…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Zeming Chen , Hang Zhao

Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the…

Artificial Intelligence · Computer Science 2025-09-09 Ruixun Liu , Lingyu Kong , Derun Li , Hang Zhao

Video generation models have made significant progress in simulating future states, showcasing their potential as world simulators in embodied scenarios. However, existing models often lack robust understanding, limiting their ability to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Xiaowei Chi , Chun-Kai Fan , Hengyuan Zhang , Xingqun Qi , Rongyu Zhang , Anthony Chen , Chi-min Chan , Wei Xue , Qifeng Liu , Shanghang Zhang , Yike Guo

Motion-controllable video generation is crucial for egocentric applications in virtual reality and embodied AI. However, existing methods often struggle to achieve 3D-consistent fine-grained hand articulation. By adopting on 2D trajectories…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Chenyangguang Zhang , Botao Ye , Boqi Chen , Alexandros Delitzas , Fangjinhua Wang , Marc Pollefeys , Xi Wang

In autonomous driving, Vision Language Models (VLMs) excel at high-level reasoning , whereas semantic occupancy provides fine-grained details. Despite significant progress in individual fields, there is still no method that can effectively…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Chenxu Dang , Jie Wang , Guang Li , Zhiwen Hou , Zihan You , Hangjun Ye , Jie Ma , Long Chen , Yan Wang

Recently, video transformers have shown great success in video understanding, exceeding CNN performance; yet existing video transformer models do not explicitly model objects, although objects can be essential for recognizing actions. In…

Computer Vision and Pattern Recognition · Computer Science 2022-06-13 Roei Herzig , Elad Ben-Avraham , Karttikeya Mangalam , Amir Bar , Gal Chechik , Anna Rohrbach , Trevor Darrell , Amir Globerson

The task of occupancy forecasting (OCF) involves utilizing past and present perception data to predict future occupancy states of autonomous vehicle surrounding environments, which is critical for downstream tasks such as obstacle avoidance…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Jingyi Xu , Xieyuanli Chen , Junyi Ma , Jiawei Huang , Jintao Xu , Yue Wang , Ling Pei

Accurate 3D perception is essential for understanding the environment in autonomous driving. Recent advancements in 3D semantic occupancy prediction have leveraged camera-LiDAR fusion to improve robustness and accuracy. However, current…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Minjae Seong , Jisong Kim , Geonho Bang , Hawook Jeong , Jun Won Choi

We present I2V3D, a novel framework for animating static images into dynamic videos with precise 3D control, leveraging the strengths of both 3D geometry guidance and advanced generative models. Our approach combines the precision of a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Zhiyuan Zhang , Dongdong Chen , Jing Liao

The emergence of Diffusion Transformers (DiT) has brought significant advancements to video generation, especially in text-to-video and image-to-video tasks. Although video generation is widely applied in various fields, most existing…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Sen Liang , Zhentao Yu , Zhengguang Zhou , Teng Hu , Hongmei Wang , Yi Chen , Qin Lin , Yuan Zhou , Xin Li , Qinglin Lu , Zhibo Chen

Multi-sensor fusion significantly enhances the accuracy and robustness of 3D semantic occupancy prediction, which is crucial for autonomous driving and robotics. However, most existing approaches depend on high-resolution images and complex…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Zhen Yang , Yanpeng Dong , Jiayu Wang , Heng Wang , Lichao Ma , Zijian Cui , Qi Liu , Haoran Pei , Kexin Zhang , Chao Zhang

This paper introduces InverseMatrixVT3D, an efficient method for transforming multi-view image features into 3D feature volumes for 3D semantic occupancy prediction. Existing methods for constructing 3D volumes often rely on depth…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Zhenxing Ming , Julie Stephany Berrio , Mao Shan , Stewart Worrall

The advent of generative radiance fields has significantly promoted the development of 3D-aware image synthesis. The cumulative rendering process in radiance fields makes training these generative models much easier since gradients are…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Xudong Xu , Xingang Pan , Dahua Lin , Bo Dai

This work presents an object-centric approach to learning vision-based manipulation skills from human videos. We investigate the problem of robot manipulation via imitation in the open-world setting, where a robot learns to manipulate novel…

Robotics · Computer Science 2025-09-05 Yifeng Zhu , Arisrei Lim , Peter Stone , Yuke Zhu

High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation, where novel-view synthesis (NVS) and time-varying information modeling are two fundamental capabilities to facilitate closed-loop training.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Bowyn Tan , Yutong Xie , Bai Huang , Fan Luo , Xiao Li , Naizheng Wang , Yang Guan , Shengbo Eben Li

Neural fields, also known as implicit neural representations (INRs), have shown a remarkable capability of representing, generating, and manipulating various data types, allowing for continuous data reconstruction at a low memory footprint.…

Image and Video Processing · Electrical Eng. & Systems 2024-02-29 Ahmed Ghorbel , Wassim Hamidouche , Luce Morin

Visual servoing enables robotic systems to perform accurate closed-loop control, which is required in many applications. However, existing methods either require precise calibration of the robot kinematic model and cameras or use neural…

Viewing omnidirectional images (ODIs) in virtual reality (VR) represents a novel form of media that provides immersive experiences for users to navigate and interact with digital content. Nonetheless, this sense of immersion can be greatly…

Human-Computer Interaction · Computer Science 2024-05-02 Zidong Cao , Zhan Wang , Yexin Liu , Yan-Pei Cao , Ying Shan , Wei Zeng , Lin Wang

Virtual Reality (VR) is becoming ubiquitous with the rise of consumer displays and commercial VR platforms. Such displays require low latency and high quality rendering of synthetic imagery with reduced compute overheads. Recent advances in…

Graphics · Computer Science 2022-07-25 Nianchen Deng , Zhenyi He , Jiannan Ye , Budmonde Duinkharjav , Praneeth Chakravarthula , Xubo Yang , Qi Sun

We present the OpenAI Remote Rendering Backend (ORRB), a system that allows fast and customizable rendering of robotics environments. It is based on the Unity3d game engine and interfaces with the MuJoCo physics simulation library. ORRB was…

Graphics · Computer Science 2019-06-28 Maciek Chociej , Peter Welinder , Lilian Weng