We present a unified formulation and model for three motion and 3D perception tasks:
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …

We propose a dense neural simultaneous localization and map** (SLAM) approach for
monocular RGBD input which anchors the features of a neural scene representation in a …

We introduce Metric3D v2, a geometric foundation model designed for zero-shot metric
depth and surface normal estimation from single images, critical for accurate 3D recovery …

Neural RGBD SLAM techniques have shown promise in dense Simultaneous Localization
And Map** (SLAM) yet face challenges such as error accumulation during camera …

Abstract Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene
representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable …

Smart manufacturing has been transforming toward industrial digitalization integrated with
various advanced technologies. Metaverse has been evolving as a next-generation …

Semantic 2D maps are commonly used by humans and machines for navigation purposes,
whether it's walking or driving. However, these maps have limitations: they lack detail, often …

Online reconstructing and rendering of large-scale indoor scenes is a long-standing
challenge. SLAM-based methods can reconstruct 3D scene geometry progressively in real …

Abstract Empowering 3D Gaussian Splatting with generalization ability is appealing.
However, existing generalizable 3D Gaussian Splatting methods are largely confined to …