cs.CV（2024-04-10）

📊 共 18 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) (9 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (9 篇)

#题目一句话要点标签🔗⭐
1 O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation 提出O2V-Mapping以解决在线开放词汇映射问题 implicit representation scene understanding open-vocabulary
2 DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting 提出DreamScene360以解决虚拟现实中3D场景生成问题 monocular depth gaussian splatting splatting
3 MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views 提出MonoSelfRecon以解决单目RGB视图下的自监督3D重建问题 depth estimation 3D reconstruction NeRF
4 Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior 提出自监督学习方法以解决水面场景的单目深度估计问题 depth estimation monocular depth
5 SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera 提出SpikeNVS以解决模糊图像下的新视角合成问题 3D gaussian splatting 3DGS gaussian splatting
6 SplatPose & Detect: Pose-Agnostic 3D Anomaly Detection 提出SplatPose以解决3D物体姿态无关的异常检测问题 3D gaussian splatting gaussian splatting splatting
7 Bayesian NeRF: Quantifying Uncertainty with Volume Density for Neural Implicit Fields 提出贝叶斯NeRF以量化体积密度的不确定性 NeRF neural radiance field
8 ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors 提出ComPC以解决3D点云补全问题 gaussian splatting splatting ✅
9 Binomial Self-compensation for Motion Error in Dynamic 3D Scanning 提出双项自补偿算法以解决动态3D扫描中的运动误差问题 3D reconstruction

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

#题目一句话要点标签🔗⭐
10 UMBRAE: Unified Multimodal Brain Decoding 提出UMBRAE以解决脑信号解码中的空间信息恢复问题 large language model multimodal ✅
11 Deep Generative Data Assimilation in Multimodal Setting 提出SLAMS以解决多模态数据同化问题 multimodal ✅
12 HRVDA: High-Resolution Visual Document Assistant 提出HRVDA以解决视觉文档理解中的低分辨率问题 large language model multimodal
13 Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding 提出uMedGround以解决医学短语识别与定位问题 large language model multimodal
14 Adapting LLaMA Decoder to Vision Transformer 提出iLLaMA以解决视觉Transformer适应性问题 large language model multimodal ✅

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

#题目一句话要点标签🔗⭐
15 RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion 提出RealmDreamer以解决文本驱动的3D场景生成问题 dreamer distillation 3D gaussian splatting
16 3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion 提出3DMambaComplete以解决点云补全中的局部细节损失问题 Mamba state space model
17 Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting 提出弱到强引导框架以提升多摄像头3D目标检测性能 distillation foundation model ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models 提出GoodDrag以解决拖拽编辑中的稳定性和图像质量问题 manipulation multimodal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页