Related papers: Complet4R: Geometric Complete 4D Reconstruction
Recent video generators achieve striking photorealism, yet remain fundamentally inconsistent in 3D. We present WorldReel, a 4D video generator that is natively spatio-temporally consistent. WorldReel jointly produces RGB frames together…
Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D…
Depth completion is crucial for many robotic tasks such as autonomous driving, 3-D reconstruction, and manipulation. Despite the significant progress, existing methods remain computationally intensive and often fail to meet the real-time…
We present a novel approach for the reconstruction of dynamic geometric shapes using a single hand-held consumer-grade RGB-D sensor at real-time rates. Our method does not require a pre-defined shape template to start with and builds up the…
Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are limited to frame rates below 30 FPS (frames per second),…
3D shape completion has broad applications in robotics, digital twin reconstruction, and extended reality (XR). Although recent advances in 3D object and scene completion have achieved impressive results, existing methods lack 3D…
Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constrains current methodologies to primarily object-centric…
Reference-driven image completion, which restores missing regions in a target view using additional images, is particularly challenging when the target view differs significantly from the references. Existing generative methods rely solely…
4D head capture aims to generate dynamic topological meshes and corresponding texture maps from videos, which is widely utilized in movies and games for its ability to simulate facial muscle movements and recover dynamic textures in…
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,…
Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native video-to-4D shape generation framework that synthesizes a single…
Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches treat these capabilities in isolation, leading to redundant pipelines and compounded…
In recent years, 3D visual foundation models pioneered by pointmap-based approaches such as DUSt3R have attracted a lot of interest, achieving impressive accuracy and strong generalization across diverse scenes. However, these methods are…
High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense…
We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered,…
Video world models aim to simulate dynamic, real-world environments, yet existing methods struggle to provide unified and precise control over camera and multi-object motion, as videos inherently capture dynamics in the projected 2D image…
Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…
We present a novel framework named NeuralRecon for real-time 3D scene reconstruction from a monocular video. Unlike previous methods that estimate single-view depth maps separately on each key-frame and fuse them later, we propose to…
This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recently, some methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when…
Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…