cs.GR（2025-04-17）
📊 共 10 篇论文
🎯 兴趣领域导航
支柱三：空间感知与语义 (Perception & Semantics) (5)
支柱一：机器人控制 (Robot Control) (2)
支柱六：视频提取与匹配 (Video Extraction) (1)
支柱九：具身大模型 (Embodied Foundation Models) (1)
支柱四：生成式动作 (Generative Motion) (1)
🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation | 提出CAGE-GS，实现基于笼状结构的3D高斯溅射形变，保持高保真度。 | 3D gaussian splatting 3DGS gaussian splatting | ||
| 2 | GSAC: Leveraging Gaussian Splatting for Photorealistic Avatar Creation with Unity Integration | GSAC：利用高斯溅射和Unity集成创建逼真化身 | 3D gaussian splatting 3DGS gaussian splatting | ||
| 3 | CompGS++: Compressed Gaussian Splatting for Static and Dynamic Scene Representation | 提出CompGS++，通过压缩高斯图元实现静态和动态场景的高效表示与压缩。 | gaussian splatting splatting TAMP | ||
| 4 | AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering | AAA-Gaussians：提出反走样和无伪影的3D高斯渲染方法 | 3D gaussian splatting 3DGS gaussian splatting | ||
| 5 | Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering | 提出Volume Encoding Gaussians (VEG)，实现与传递函数无关的体绘制3D高斯模型。 | 3D gaussian splatting 3DGS gaussian splatting |
🔬 支柱一：机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | ARAP-GS: Drag-driven As-Rigid-As-Possible 3D Gaussian Splatting Editing with Diffusion Prior | ARAP-GS：提出基于扩散先验的拖拽式As-Rigid-As-Possible 3D高斯溅射编辑方法 | manipulation 3D gaussian splatting 3DGS | ||
| 7 | UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control | UniPhys：基于扩散模型的统一规划与控制框架，实现灵活的物理角色控制 | motion planning behavior cloning physically plausible |
🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models | SMPL-GPTexture：利用文本到图像生成模型实现双视角3D人体纹理估计 | human mesh recovery SMPL |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | 3D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noise | 提出基于Perlin噪声的3D工业表面缺陷合成方法3D-PNAS，用于解决工业缺陷检测中3D数据匮乏问题。 | foundation model |
🔬 支柱四：生成式动作 (Generative Motion) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materials | SOPHY：学习生成具有物理材质的、可用于仿真的3D物体 | physically plausible |