Efficient Neural Supersampling on a Novel Gaming Dataset

在新颖的游戏数据集上进行高效的神经超级采样

Locally Stylized Neural Radiance Fields

局部风格化神经辐射场

NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects

NEMTO：用于新颖视图的神经环境抠图和透明物体的重新照明合成

DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

DDColor：通过双解码器实现照片级真实感图像着色

IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

IntrinsicNeRF：学习内在神经辐射场以进行可编辑的小说视图合成

PARIS: Part-Level Reconstruction and Motion Analysis for Articulated Objects

巴黎：铰接物体的部分级重建和运动分析

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

ReMoDiffuse：检索增强运动扩散模型

DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion

DS-Fusion：通过区分和风格化扩散的艺术版式

Neural Microfacet Fields for Inverse Rendering

用于逆向渲染的神经微面场

A Theory of Topological Derivatives for Inverse Rendering of Geometry

几何逆绘制的拓扑导数理论

Vox-E: Text-Guided Voxel Editing of 3D Objects

Vox-E：文本引导的 3D 对象体素编辑

StegaNeRF: Embedding Invisible Information within Neural Radiance Fields

StegaNeRF：在神经辐射场中嵌入不可见信息

GlobalMapper: Arbitrary-Shaped Urban Layout Generation

GlobalMapper：任意形状的城市布局生成

Urban Radiance Field Representation with Deformable Neural Mesh Primitives

使用可变形神经网格基元的城市辐射场表示

End2End Multi-View Feature Matching with Differentiable Pose Optimization

具有可微姿态优化的端到端多视图特征匹配

AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism

AttT2M：具有多视角注意机制的文本驱动人体运动生成

Computationally-Efficient Neural Image Compression with Shallow Decoders

使用浅层解码器的计算高效的神经图像压缩