cs.CV（2025-12-09）
📊 共 8 篇论文
🎯 兴趣领域导航
支柱三：空间感知与语义 (Perception & Semantics) (3)
支柱二：RL算法与架构 (RL & Architecture) (2)
支柱一：机器人控制 (Robot Control) (2)
支柱九：具身大模型 (Embodied Foundation Models) (1)
🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars | GTAvatar：结合高斯溅射与纹理映射，实现可重光照和编辑的高斯头像 | gaussian splatting splatting | ||
| 2 | Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment | Selfi：通过3D几何特征对齐实现自提升的新视角合成引擎 | VGGT geometric consistency foundation model | ||
| 3 | SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking | 提出SDT-6D，用于工业多视角分拣中端到端6D位姿估计的全稀疏深度Transformer | 6D pose estimation |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform | Visionary：基于WebGPU高斯溅射的世界模型浏览器平台 | world model 3D gaussian splatting 3DGS | ||
| 5 | Beyond Real Weights: Hypercomplex Representations for Stable Quantization | 提出基于超复数表示的渐进式重参数化方法，实现多模态大模型的高效量化。 | distillation multimodal |
🔬 支柱一：机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Geometry-Aware Sparse Depth Sampling for High-Fidelity RGB-D Depth Completion in Robotic Systems | 提出几何感知稀疏深度采样，提升机器人RGB-D深度补全精度 | manipulation | ||
| 7 | Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation | Terrain Diffusion：基于扩散模型的实时无限地形生成，替代Perlin噪声 | manipulation |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | RLCNet: An end-to-end deep learning framework for simultaneous online calibration of LiDAR, RADAR, and Camera | 提出RLCNet，用于激光雷达、雷达和相机在线联合标定的端到端深度学习框架 | multimodal |