Related papers: Know Your Neighbors: Improving Single-View Reconst…

3D face reconstruction is a fundamental Computer Vision problem of extraordinary difficulty. Current systems often assume the availability of multiple facial images (sometimes from the same subject) as input, and must address a number of…

Active 3D reconstruction enables an agent to autonomously select viewpoints to efficiently obtain accurate and complete scene geometry, rather than passively reconstructing scenes from pre-collected images. However, existing active…

Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry. We avoid all such supervision and assumptions by…

In crowded urban environments where traffic is dense, current technologies struggle to oversee tight navigation, but surface-level understanding allows autonomous vehicles to safely assess proximity to surrounding obstacles. 3D or 2D scene…

This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images. Many previous works have shown impressive reconstruction results on textured objects, but they still have difficulty in handling low-textured…

Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard…

Reconstructing outdoor 3D scenes from temporal observations is a challenge that recent work on neural fields has offered a new avenue for. However, existing methods that recover scene properties, such as geometry, appearance, or radiance,…

The vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, the presence of dynamic objects in the scene seriously affects the accuracy of the model…

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 reconstruction mostly adopt a volumetric scheme, where a Truncated…

In this paper, we propose a novel method for joint recovery of camera pose, object geometry and spatially-varying Bidirectional Reflectance Distribution Function (svBRDF) of 3D scenes that exceed object-scale and hence cannot be captured…

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…

Semantic scene reconstruction from point cloud is an essential and challenging task for 3D scene understanding. This task requires not only to recognize each instance in the scene, but also to recover their geometries based on the partial…

Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned…

A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparatively, 3D poses new…

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such…

Light detection and ranging (Lidar) data can be used to capture the depth and intensity profile of a 3D scene. This modality relies on constructing, for each pixel, a histogram of time delays between emitted light pulses and detected photon…

The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by…

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,…

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…

Single image view synthesis allows for the generation of new views of a scene given a single input image. This is challenging, as it requires comprehensively understanding the 3D scene from a single image. As a result, current methods…