cs.CV(2023-12-02)

📊 共 11 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (4) 支柱四:生成式动作 (Generative Motion) (2) 支柱九:具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱三:空间感知与语义 (Perception & Semantics) (2) 支柱七:动作重定向 (Motion Retargeting) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗
1 StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D 提出StableDreamer以解决文本到3D生成中的噪声问题 dreamer distillation NeRF
2 Self-Evolving Neural Radiance Fields 提出自进化神经辐射场(SE-NeRF),解决稀疏视角下NeRF过拟合问题。 teacher-student distillation NeRF
3 S2P3: Self-Supervised Polarimetric Pose Prediction 提出基于偏振RGB图像的自监督6D物体姿态预测方法,解决无纹理/反射/透明物体姿态估计难题。 teacher-student distillation multimodal
4 ControlDreamer: Blending Geometry and Style in Text-to-3D ControlDreamer:融合几何与风格的文本到3D生成方法 dreamer

🔬 支柱四:生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗
5 AAMDM: Accelerated Auto-regressive Motion Diffusion Model 提出AAMDM加速自回归运动扩散模型,提升交互式运动合成的质量、多样性和效率 motion diffusion model motion diffusion motion synthesis
6 QPoser: Quantized Explicit Pose Prior Modeling for Controllable Pose Generation QPoser:量化的显式姿态先验模型,实现可控的姿态生成 VQ-VAE

🔬 支柱九:具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗
7 A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detection 提出基于Foundation Model的双时相遥感影像变化检测框架BAN,提升现有方法性能。 foundation model
8 Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling 提出基于掩码建模的音视频早期融合Transformer,提升多模态感知能力 multimodal

🔬 支柱三:空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗
9 DPHMs: Diffusion Parametric Head Models for Depth-based Tracking 提出基于扩散参数化头部模型的深度跟踪方法,提升单目深度序列头部重建与跟踪的鲁棒性。 monocular depth
10 Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D Diffusion Handles:通过将激活提升到3D空间实现扩散模型的三维编辑 depth estimation

🔬 支柱七:动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗
11 RobustCalib: Robust Lidar-Camera Extrinsic Calibration with Consistency Learning 提出RobustCalib,通过一致性学习实现鲁棒的激光雷达-相机外参标定 geometric consistency

⬅️ 返回 cs.CV 首页 · 🏠 返回主页