Related papers: InfiniteVGGT: Visual Geometry Grounded Transformer…
Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explosion of visual tokens, which often leads to Out-of-Memory…
Recently, Vision Graph Neural Network (ViG) has gained considerable attention in computer vision. Despite its groundbreaking innovation, Vision Graph Neural Network encounters key issues including the quadratic computational complexity…
Autoregressive models have achieved remarkable success across various domains, yet their performance in 3D shape generation lags significantly behind that of diffusion models. In this paper, we introduce OctGPT, a novel multiscale…
Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…
Graph Transformers (GTs) have recently demonstrated remarkable performance across diverse domains. By leveraging attention mechanisms, GTs are capable of modeling long-range dependencies and complex structural relationships beyond local…
Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…
Understanding and localizing objects in complex 3D environments from natural language descriptions, known as 3D Visual Grounding (3DVG), is a foundational challenge in embodied AI, with broad implications for robotics, augmented reality,…
We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets…
Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal…
Image-based 3D generation has vast applications in robotics and gaming, where high-quality, diverse outputs and consistent 3D representations are crucial. However, existing methods have limitations: 3D diffusion models are limited by…
Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from context limitations, visual drift due to positional…
Closed-loop evaluation of autonomous-driving policies requires interactive simulation beyond log replay. However, existing generative world models often degrade in closed loop due to (i) history-free initialization that mismatches policy…
Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…
While streaming omni-video understanding demands continuous perception and proactive, real-time interaction, this crucial area remains largely under-explored. Current omni-modal methods are inherently designed for offline settings, limiting…
Generalizing a pretrained model to unseen datasets without retraining is an essential step toward a foundation model. However, achieving such cross-dataset, fully inductive inference is difficult in graph-structured data where feature…
State-of-the-art 3D computer vision algorithms continue to advance in handling sparse, unordered image sets. Recently developed foundational models for 3D reconstruction, such as Dense and Unconstrained Stereo 3D Reconstruction (DUSt3R),…
Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory. However, their advantage in terms of…
While Multimodal Large Language Models demonstrate impressive semantic capabilities, they often suffer from spatial blindness, struggling with fine-grained geometric reasoning and physical dynamics. Existing solutions typically rely on…
In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for…
Accurate vascular segmentation is essential for coronary visualization and the diagnosis of coronary heart disease. This task involves the extraction of sparse tree-like vascular branches from the volumetric space. However, existing methods…