Abstract Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralFiel

Normalization——Batch Norm, Layer Norm, Instance Norm and Group NormNormalizationFor a tensor with the shape of (N, C, D), where $N$ stands for batch-size, $C$ stands for features and D stands for feat

3D Shape RepresentationsExplicit RepresentationThe description of a scene is explicit, and the 3D representation of the scene can be seen directly, such as mesh, point cloud, voxel and volume which ca

Review of PointNetOne of the most prominent shortcomings of PointNet is that PointNet does not capture local structures induced by the metric space points live in, because PointNet only extract featur

Point Cloud DataPoint cloud data refers to a set of vectors in a 3D coordinate system. A normal point cloud object is usually with 2D shape (n, 3+X), where n is the number of points, 3 stands for 3D c

Vision TransformerInductive biasVision Transformer has much less image-specific inductive bias than CNNs. In CNNs, locality, two-dimensional neighborhood structure, and translation equivariance are ba

Input/Output Representations Fig.1 Input Represention For handling a variety of down-stream tasks, the input representation of BERT is able to unambiguously represent both a single sen

Abstract In this work, we present a novel framework built to simplify 3D asset generation for amateur users. To enable interactive generation, our method supports a variety of input modalities that ca

Basics of ProbabilityConditional Probability \begin{aligned} P(A, B, C) & = P(C|A, B)P(A, B) = P(C|A, B)P(B|A)P(A) \\ P(B, C|A) & = \frac{P(A, B, C)}{P(A)} = P(C|A, B)P(B

Motivation Applying diffusion models to other modalities has been successful, but requires large amounts of modality-specific training data. 3D assetsare currently designed by hand in modeling softwar