Traditionally, 3D indoor scene reconstruction from posed images happens in two phases:
per-image depth estimation, followed by depth merging and surface reconstruction …

In this work we introduce ProMotion a unified prototypical transformer-based framework
engineered to model fundamental motion tasks. ProMotion offers a range of compelling …

Recent works on 3D reconstruction from posed images have demonstrated that direct
inference of scene-level 3D geometry without test-time optimization is feasible using deep …

Recent advances in neural reconstruction using posed image sequences have made
remarkable progress. However, due to the lack of depth information, existing volumetric …

A key challenge in neural 3D scene reconstruction from monocular images is to fuse
features back projected from various views without any depth or occlusion information. We …

We propose VisFusion, a visibility-aware online 3D scene reconstruction approach from
posed monocular videos. In particular, we aim to reconstruct the scene from volumetric …

The perception module of self-driving vehicles relies on a multi-sensor system to understand
its environment. Recent advancements in deep learning have led to the rapid development …

We present a novel neural surface reconstruction method called NeuralRoom for
reconstructing room-sized indoor scenes directly from a set of 2D images. Recently, implicit …

We present a novel real-time capable learning method that jointly perceives a 3D scene's
geometry structure and semantic labels. Recent approaches to real-time 3D scene …

In this work, we propose a real-time monocular 3D video reconstruction approach named
Flora for reconstructing delicate and complete 3D scenes from RGB video sequences in an …