Existing neural field representations for 3D object reconstruction either (1)
utilize object-level representations, but suffer from low-quality details due
to conditioning on a global latent code, or (2) are able to perfectly
reconstruct the observations, but fail to utilize object-level prior knowledge
to infer unobserved regions. We present SimNP, a method to learn category-level
self-similarities, which combines the advantages of both worlds by connecting
neural point radiance fields with a category-level self-similarity
representation. Our contribution is two-fold. (1) We design the first neural
point representation on a category level by utilizing the concept of coherent
point clouds. The resulting neural point radiance fields store a high level of
detail for locally supported object regions. (2) We learn how information is
shared between neural points in an unconstrained and unsupervised fashion,
which allows to derive unobserved regions of an object during the
reconstruction process from given observations. We show that SimNP is able to
outperform previous methods in reconstructing symmetric unseen object regions,
surpassing methods that build upon category-level or pixel-aligned radiance
fields, while providing semantic correspondences between instances

利用类别层次的自相似性连接神经点辐射场和神经点，通过学习四维对象重建方法，SimNP 能在提供语义对应的同时重建无法观测到的对称未见的对象区域，优于以往的方法。

SimNP：学习神经点之间的自相似先验

SimNP: Learning Self-Similarity Priors Between Neural Points

Indoor scene reconstruction from monocular images has long been sought after
by augmented reality and robotics developers. Recent advances in neural field
representations and monocular priors have led to remarkable results in
scene-level surface reconstructions. The reliance on Multilayer Perceptrons
(MLP), however, significantly limits speed in training and rendering. In this
work, we propose to directly use signed distance function (SDF) in sparse voxel
block grids for fast and accurate scene reconstruction without MLPs. Our
globally sparse and locally dense data structure exploits surfaces' spatial
sparsity, enables cache-friendly queries, and allows direct extensions to
multi-modal data such as color and semantic labels. To apply this
representation to monocular scene reconstruction, we develop a scale
calibration algorithm for fast geometric initialization from monocular depth
priors. We apply differentiable volume rendering from this initialization to
refine details with fast convergence. We also introduce efficient
high-dimensional Continuous Random Fields (CRFs) to further exploit the
semantic-geometry consistency between scene objects. Experiments show that our
approach is 10x faster in training and 100x faster in rendering while achieving
comparable accuracy to state-of-the-art neural implicit methods.

研究使用 “符号距离函数” 结合 “稀疏体素块网格” 等算法实现室内场景的平面重建，相较于常规算法在训练与渲染速度上有数量级的提升，同时保持与现有方法相当的精度。

基于全局稀疏 - 局部稠密格点的快速单目场景重建

Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids

We present vMAP, an object-level dense SLAM system using neural field
representations. Each object is represented by a small MLP, enabling efficient,
watertight object modelling without the need for 3D priors. As an RGB-D camera
browses a scene with no prior information, vMAP detects object instances
on-the-fly, and dynamically adds them to its map. Specifically, thanks to the
power of vectorised training, vMAP can optimise as many as 50 individual
objects in a single scene, with an extremely efficient training speed of 5Hz
map update. We experimentally demonstrate significantly improved scene-level
and object-level reconstruction quality compared to prior neural field SLAM
systems. Project page: this https URL

vMAP 采用神经场表示法实现目标级别的稠密 SLAM 系统。每个目标都由小型 MLP 表示，实现高效和完整的建模，无需 3D 先验知识。通过 RGB-D 相机，vMAP 可以在不需要先验信息的情况下实时检测对象实例并将其动态添加到地图中。该系统可以在单个场景中优化多达 50 个独立的目标，并实现高效的训练速度，更新频率达到 5 Hz。与先前的神经场 SLAM 系统相比，实验证明了显著改善的场景级别和目标级别重构质量。