Related papers: OmniWorld: A Multi-Domain and Multi-Modal Dataset …
Omnidirectional images (ODIs) provide full 360x180 view which are widely adopted in VR, AR and embodied intelligence applications. While multi-modal large language models (MLLMs) have demonstrated remarkable performance on conventional 2D…
Robotic world models are a promising paradigm for forecasting future environment states, yet their inference speed and the physical plausibility of generated trajectories remain critical bottlenecks, limiting their real-world applications.…
Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying rules that govern environment dynamics. In this work, we address this open…
Recent research on representation learning has proved the merits of multi-modal clues for robust semantic segmentation. Nevertheless, a flexible pretrain-and-finetune pipeline for multiple visual modalities remains unexplored. In this…
Omnidirectional image (ODI) data is captured with a field-of-view of 360x180, which is much wider than the pinhole cameras and captures richer surrounding environment details than the conventional perspective images. In recent years, the…
Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual…
Dense 3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision. Progress in this area has been constrained by the scarcity of high-quality datasets with dense, complete,…
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in various multimodal tasks. However, their potential in the medical domain remains largely unexplored. A significant challenge arises from the scarcity of…
Omnidirectional or 360-degree video is being increasingly deployed, largely due to the latest advancements in immersive virtual reality (VR) and extended reality (XR) technology. However, the adoption of these videos in streaming encounters…
Monocular 3D tracking aims to capture the long-term motion of pixels in 3D space from a single monocular video and has witnessed rapid progress in recent years. However, we argue that the existing monocular 3D tracking methods still fall…
Reliable anticipation of traffic accidents is essential for advancing autonomous driving systems. However, this objective is limited by two fundamental challenges: the scarcity of diverse, high-quality training data and the frequent absence…
Computational fluid dynamics (CFD) drives progress in numerous scientific and engineering fields, yet high-fidelity simulations remain computationally prohibitive. While machine learning approaches offer computing acceleration, they…
Federated learning (FL) has become a promising paradigm for collaborative medical image analysis, yet existing frameworks remain tightly coupled to task-specific backbones and are fragile under heterogeneous imaging modalities. Such…
In this paper, we introduce OmniEval, a benchmark for evaluating omni-modality models like MiniCPM-O 2.6, which encompasses visual, auditory, and textual inputs. Compared with existing benchmarks, our OmniEval has several distinctive…
Face forgery detection encompasses multiple critical tasks, including identifying forged images and videos and localizing manipulated regions and temporal segments. Current approaches typically employ task-specific models with independent…
World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research…
Multi-object tracking in traffic videos is a crucial research area, offering immense potential for enhancing traffic monitoring accuracy and promoting road safety measures through the utilisation of advanced machine learning algorithms.…
3D scene generation has garnered growing attention in recent years and has made significant progress. Generating 4D cities is more challenging than 3D scenes due to the presence of structurally complex, visually diverse objects like…
In this paper, we propose NeoVerse, a versatile 4D world model that is capable of 4D reconstruction, novel-trajectory video generation, and rich downstream applications. We first identify a common limitation of scalability in current 4D…
High-precision navigation and positioning systems are critical for applications in autonomous vehicles and mobile mapping, where robust and continuous localization is essential. To test and enhance the performance of algorithms, some…