Related papers: HoloScene: Simulation-Ready Interactive 3D Worlds …
We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric…
Neural rendering has demonstrated remarkable success in dynamic scene reconstruction. Thanks to the expressiveness of neural representations, prior works can accurately capture the motion and achieve high-fidelity reconstruction of the…
Creating a photorealistic scene and human reconstruction from a single monocular in-the-wild video figures prominently in the perception of a human-centric 3D world. Recent neural rendering advances have enabled holistic human-scene…
Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propose a novel framework, empowered by a 2D diffusion-based…
Interactive 3D scene generation from a single image has gained significant attention due to its potential to create immersive virtual worlds. However, a key challenge in current 3D generation methods is the limited explorability, which…
3D reconstruction has been widely used in autonomous navigation fields of mobile robotics. However, the former research can only provide the basic geometry structure without the capability of open-world scene understanding, limiting…
3D scene reconstruction is a foundational problem in computer vision. Despite recent advancements in Neural Implicit Representations (NIR), existing methods often lack editability and compositional flexibility, limiting their use in…
Monocular 3D scene reconstruction has recently seen significant progress. Powered by the modern neural architectures and large-scale data, recent methods achieve high performance in depth estimation from a single image. Meanwhile,…
We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing Neural SLAM or 3DGS-based SLAM methods often trade off between rendering quality and…
High dynamic range (HDR) video reconstruction from sequences captured with alternating exposures is a very challenging problem. Existing methods often align low dynamic range (LDR) input sequence in the image space using optical flow, and…
While feed-forward 3D reconstruction models have advanced rapidly, they still exhibit degraded performance on panoramas due to spherical distortions. Moreover, existing panoramic 3D datasets are predominantly collected with 360 cameras…
We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable…
The recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated remarkable potential in novel view synthesis tasks. The divide-and-conquer paradigm has enabled large-scale scene reconstruction, but significant challenges remain in…
3D understanding is a key capability for real-world AI assistance. High-quality data plays an important role in driving the development of the 3D understanding community. Current 3D scene understanding datasets often provide geometric and…
Sharing live telepresence experiences for teleconferencing or remote collaboration receives increasing interest with the recent progress in capturing and AR/VR technology. Whereas impressive telepresence systems have been proposed on top of…
The ability to accurately reconstruct the 3D facets of a scene is one of the key problems in robotic vision. However, even with recent advances with machine learning, there is no high-fidelity universal 3D reconstruction method for this…
This paper develops a simple and fast method to reconstruct reality from stereoscopic images. We bring together ideas from robust optical flow techniques, morphing deformations and lightfield 3D rendering in order to create unsupervised…
Previous surface reconstruction methods either suffer from low geometric accuracy or lengthy training times when dealing with real-world complex dynamic scenes involving multi-person activities, and human-object interactions. To tackle the…
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…
We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene…