cs.CV（2024-02-22）

📊 共 26 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (10 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (8 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (10 篇)

#题目一句话要点标签🔗⭐
1 Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields 提出Mip-Grid以解决神经辐射场中的别名问题 NeRF neural radiance field ✅
2 GaussianPro: 3D Gaussian Splatting with Progressive Propagation 提出GaussianPro以解决3D Gaussian Splatting初始化不足问题 3D gaussian splatting 3DGS gaussian splatting
3 An Error-Matching Exclusion Method for Accelerating Visual SLAM 提出一种误差匹配排除方法以加速视觉SLAM visual SLAM feature matching
4 GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints 提出GAM-Depth以解决室内深度估计中的不一致性问题 depth estimation ✅
5 MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion 提出MVD$^2$以解决多视图扩散图像的3D重建问题 3D reconstruction
6 Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding 提出Swin3D++以解决3D室内场景理解中的数据多样性问题 scene understanding ✅
7 TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization 提出TaylorGrid以解决隐式场学习速度与质量的平衡问题 NeRF implicit representation
8 Cameras as Rays: Pose Estimation via Ray Diffusion 提出基于光线扩散的相机姿态估计方法以解决稀疏视图问题 3D reconstruction
9 FrameNeRF: A Simple and Efficient Framework for Few-shot Novel View Synthesis 提出FrameNeRF以解决少样本新视角合成问题 NeRF
10 Semantic Image Synthesis with Unconditional Generator 提出无条件生成器以解决语义图像合成问题 semantic map

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
11 Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image 提出停推理攻击以增强多模态大语言模型的对抗鲁棒性 multimodal chain-of-thought
12 Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models 提出Mudjacking以解决基础模型后门漏洞问题 foundation model
13 Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset 提出MATH-Vision数据集以解决多模态数学推理问题 multimodal
14 DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models 提出DualFocus框架以解决多模态大语言模型的局部细节问题 large language model
15 Visual Hallucinations of Multi-modal Large Language Models 提出VHTest工具以解决多模态大语言模型的视觉幻觉问题 large language model ✅
16 Unsupervised Domain Adaptation within Deep Foundation Latent Spaces 提出无监督领域适应方法以优化深度基础模型 foundation model
17 WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition 提出WeakSAM以解决弱监督实例级识别问题 foundation model ✅
18 Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition 提出无缝适应预训练模型以解决视觉地点识别问题 foundation model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
19 TIE-KD: Teacher-Independent and Explainable Knowledge Distillation for Monocular Depth Estimation 提出TIE-KD框架以解决单目深度估计中的知识蒸馏问题 distillation depth estimation monocular depth
20 NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection 提出NeRF-Det++以解决室内多视角3D检测中的语义模糊问题 representation learning NeRF semantic map ✅
21 CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion 提出CLCE以解决交叉熵与对比学习融合问题 contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
22 Consolidating Attention Features for Multi-view Image Editing 提出QNeRF以解决多视图图像编辑中的几何一致性问题 manipulation NeRF neural radiance field
23 Typographic Text Generation with Off-the-Shelf Diffusion Model 提出基于扩散模型的排版文本生成系统以解决样式指定问题 manipulation

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
24 Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot 提出Multi-HMR以解决单张RGB图像中的多人体全身网格恢复问题 human mesh recovery HMR SMPL

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

#题目一句话要点标签🔗⭐
25 Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis 提出Snap Video以解决视频生成中的运动保真度和可扩展性问题 spatiotemporal ✅

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
26 GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion 提出GeneOH Diffusion以解决手-物体交互去噪问题 HOI ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页