cs.CV（2024-04-21）

📊 共 13 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱七：动作重定向 (Motion Retargeting) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
1 Universal Fingerprint Generation: Controllable Diffusion Model with Multimodal Conditions 提出GenPrint以解决指纹生成中的多样性问题 multimodal
2 Interpreting COVID Lateral Flow Tests' Results with Foundation Models 利用基础模型自动解读COVID快速检测结果 foundation model ✅
3 LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing 提出LMFNet以解决高分辨率遥感图像多模态融合问题 multimodal
4 FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization 提出FiLo以解决零样本异常检测中的描述与定位问题 large language model multimodal ✅
5 MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning 提出MARVEL基准以评估多模态大语言模型的抽象视觉推理能力 large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
6 GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal 提出GScream以解决三维几何一致性和纹理连贯性问题 depth estimation monocular depth 3D gaussian splatting
7 Attack on Scene Flow using Point Clouds 提出针对场景流的对抗攻击以提升鲁棒性 optical flow scene flow ✅
8 Generalizable Novel-View Synthesis using a Stereo Camera 提出StereoNeRF以解决多视角立体相机图像的新视角合成问题 stereo depth NeRF
9 Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence 提出Segment-then-Restore方法以解决动态视频中的大气湍流问题 optical flow

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#题目一句话要点标签🔗⭐
10 MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions 提出运动标签先验以解决人类动作的时间句子定位问题 human motion ✅
11 Motion-aware Latent Diffusion Models for Video Frame Interpolation 提出运动感知潜在扩散模型以解决视频帧插值问题 motion estimation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
12 Zero-shot High-fidelity and Pose-controllable Character Animation 提出PoseAnimate以解决高保真与姿态可控角色动画问题 character animation

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
13 ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face Synthesis 提出ArtNeRF以解决3D感知卡通脸合成问题 contrastive learning NeRF neural radiance field

⬅️ 返回 cs.CV 首页 · 🏠 返回主页