Related papers: Unsigned Distance Field as an Accurate 3D Scene Re…

Neural fields, coordinate-based neural networks, have recently gained popularity for implicitly representing a scene. In contrast to classical methods that are based on explicit representations such as point clouds, neural fields provide a…

Optimization-based trajectory generation methods are widely used in whole-body planning for robots. However, existing work either oversimplifies the robot's geometry and environment representation, resulting in a conservative trajectory, or…

Unsigned distance fields (UDFs) offer broader modeling capabilities than signed distance fields (SDFs), enabling the representation of shapes with open boundaries, non-manifold structures or mixed curve and surface parts. However,…

We present a method to reconstruct indoor and outdoor static scene geometry and appearance from an omnidirectional video moving in a small circular sweep. This setting is challenging because of the small baseline and large depth ranges,…

Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online…

In recent years, implicit surface representations through neural networks that encode the signed distance have gained popularity and have achieved state-of-the-art results in various tasks (e.g. shape representation, shape reconstruction,…

Faster rendering of synthetic images is a core problem in the field of computer graphics. Rendering algorithms, such as path-tracing is dependent on parameters like size of the image, number of light bounces, number of samples per pixel,…

A long-standing goal in scene understanding is to obtain interpretable and editable representations that can be directly constructed from a raw monocular RGB-D video, without requiring specialized hardware setup or priors. The problem is…

While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains a challenge. Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) offer powerful…

Building accurate maps is a key building block to enable reliable localization, planning, and navigation of autonomous vehicles. We propose a novel approach for building accurate maps of dynamic environments utilizing a sequence of LiDAR…

This study proposes a neural disparity field (NDF) that establishes an implicit, continuous representation of scene disparity based on a neural field and an iterative approach to address the inverse problem of NDF reconstruction from…

We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground…

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for…

Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant…

Current methods based on Neural Radiance Fields (NeRF) significantly lack the capacity to quantify uncertainty in their predictions, particularly on the unseen space including the occluded and outside scene content. This limitation hinders…

3D semantic scene understanding is a fundamental challenge in computer vision. It enables mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes this challenge as jointly estimating dense geometry and…

Recently, there has been an increased interest in NeRF methods which reconstruct differentiable representation of three-dimensional scenes. One of the main limitations of such methods is their inability to assess the confidence of the model…

Robust scene representation is essential for autonomous systems to safely operate in challenging low-visibility environments. Radar has a clear advantage over cameras and lidars in these conditions due to its resilience to environmental…

Learning-based surface reconstruction based on unsigned distance functions (UDF) has many advantages such as handling open surfaces. We propose SuperUDF, a self-supervised UDF learning which exploits a learned geometry prior for efficient…

Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape. Previous approaches propose neural networks to directly estimate the whole point cloud through…