Related papers: G2D: from GTA to Data
Temporal action detection is a fundamental yet challenging task in video understanding. Video context is a critical cue to effectively detect actions, but current works mainly focus on temporal context, while neglecting semantic context as…
End-to-end autonomous driving has evolved from the conventional paradigm based on sparse perception into vision-language-action (VLA) models, which focus on learning language descriptions as an auxiliary task to facilitate planning. In this…
We present a real-time approach for image-based localization within large scenes that have been reconstructed offline using structure from motion (Sfm). From monocular video, our method continuously computes a precise 6-DOF camera pose, by…
State-of-the-art novel view synthesis methods achieve impressive results for multi-view captures of static 3D scenes. However, the reconstructed scenes still lack "liveliness," a key component for creating engaging 3D experiences. Recently,…
This paper presents GSWorld, a robust, photo-realistic simulator for robotics manipulation that combines 3D Gaussian Splatting with physics engines. Our framework advocates "closing the loop" of developing manipulation policies with…
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…
For driver observation frameworks, clean datasets collected in controlled simulated environments often serve as the initial training ground. Yet, when deployed under real driving conditions, such simulator-trained models quickly face the…
Urban scene reconstruction requires modeling both static infrastructure and dynamic elements while supporting diverse environmental conditions. We present \textbf{StyledStreets}, a multi-style street simulator that achieves…
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows,…
The aim of this paper is to propose new algorithms for Field of Vision (FOV) computation which improve on existing work at high resolutions. FOV refers to the set of locations that are visible from a specific position in a scene of a…
Recent high-performing image-to-video (I2V) models based on variants of the diffusion transformer (DiT) have displayed remarkable inherent world-modeling capabilities by virtue of training on large scale video datasets. We investigate…
Building recognition and 3D reconstruction of human made structures in urban scenarios has become an interesting and actual topic in the image processing domain. For this research topic the Computer Vision and Augmented Reality areas…
Digital twin is a problem of augmenting real objects with their digital counterparts. It can underpin a wide range of applications in augmented reality (AR), autonomy, and UI/UX. A critical component in a good digital-twin system is…
Traffic congestion in urban areas presents significant challenges, and Intelligent Transportation Systems (ITS) have sought to address these via automated and adaptive controls. However, these systems often struggle to transfer simulated…
Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet they remain constrained by scarce annotated real-world V2X driving datasets and limited…
Different video understanding tasks are typically treated in isolation, and even with distinct types of curated data (e.g., classifying sports in one dataset, tracking animals in another). However, in wearable cameras, the immersive…
Embodied intelligence requires high-fidelity simulation environments to support perception and decision-making, yet existing platforms often suffer from data contamination and limited flexibility. To mitigate this, we propose…
For 6-DoF grasp detection, simulated data is expandable to train more powerful model, but it faces the challenge of the large gap between simulation and real world. Previous works bridge this gap with a sim-to-real way. However, this way…
Synthesizing controllable 6-DOF object manipulation trajectories in 3D environments is essential for enabling robots to interact with complex scenes, yet remains challenging due to the need for accurate spatial reasoning, physical…
Generating complex multi-actor scenario videos remains difficult even for state-of-the-art neural generators, while evaluating them is hard due to the lack of ground truth for physical plausibility and semantic faithfulness. We introduce…