cs.CV（2024-02-07）

📊 共 16 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (8 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (8 篇)

#题目一句话要点标签🔗⭐
1 OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding 提出OV-NeRF以解决开放词汇3D语义感知问题 NeRF neural radiance field open-vocabulary ✅
2 FM-Fusion: Instance-aware Semantic Mapping Boosted by Vision-Language Foundation Models 提出FM-Fusion以提升实例感知语义映射的准确性 semantic mapping semantic map foundation model
3 LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors 提出DVDet以提升开放词汇物体检测的精确性 open-vocabulary open vocabulary large language model
4 Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration 提出级联深度估计与校准以解决相机3D目标检测精度问题 depth estimation
5 Shape-biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation 提出形状偏置的纹理无关表示以改善无纹理和金属物体检测 6D pose estimation
6 NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Rendering 提出NeRF作为非远程环境发射器以解决逆向渲染中的光照问题 NeRF
7 GSN: Generalisable Segmentation in Neural Radiance Field 提出GSN以解决神经辐射场中的可泛化分割问题 neural radiance field ✅
8 Detection and Pose Estimation of flat, Texture-less Industry Objects on HoloLens using synthetic Training 提出基于合成训练的AR应用以解决工业物体姿态估计问题 6D pose estimation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
9 ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation 提出ColorSwap数据集以评估多模态模型的颜色与词序匹配能力 multimodal ✅
10 $λ$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space 提出$λ$-ECLIPSE以解决个性化文本到图像生成的资源效率问题 large language model multimodal
11 InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior 提出InstructScene以解决3D室内场景合成的可控性问题 multimodal ✅

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

#题目一句话要点标签🔗⭐
12 BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designs 提出BIKED++数据集以促进参数化与图像设计的跨模态学习 predictive model multimodal ✅
13 Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation 提出Mamba-UNet以解决医学图像分割中的长距离依赖问题 Mamba SSM state space model
14 Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance Segmentation 提出边界感知对比学习以解决半监督细胞核实例分割问题 contrastive learning

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

#题目一句话要点标签🔗⭐
15 SAMCIRT: A Simultaneous Reconstruction and Affine Motion Compensation Technique for Four Dimensional Computed Tomography (4DCT) 提出SAMCIRT以解决4DCT重建与运动补偿问题 motion estimation

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

#题目一句话要点标签🔗⭐
16 Spiking-PhysFormer: Camera-Based Remote Photoplethysmography with Parallel Spike-driven Transformer 提出Spiking-PhysFormer以解决移动设备上rPPG的能耗问题 PULSE

⬅️ 返回 cs.CV 首页 · 🏠 返回主页