cs.CV（2023-11-22）

📊 共 22 篇论文 | 🔗 12 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (12 🔗5) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (12 篇)

#题目一句话要点标签🔗⭐
1 Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images 提出深度正则化优化方法以解决少量图像下的3D高斯点云过拟合问题 depth estimation monocular depth 3D gaussian splatting
2 Animatable 3D Gaussians for High-fidelity Synthesis of Human Motions 提出可动画的3D高斯模型以解决人类动作合成问题 NeRF human motion
3 Compact 3D Gaussian Representation for Radiance Field 提出紧凑的3D高斯表示以解决NeRF渲染瓶颈问题 3D gaussian splatting 3DGS gaussian splatting ✅
4 3D Face Style Transfer with a Hybrid Solution of NeRF and Mesh Rasterization 提出混合解决方案以实现一致性的3D人脸风格迁移 NeRF neural radiance field
5 Two-stage Synthetic Supervising and Multi-view Consistency Self-supervising based Animal 3D Reconstruction by Single Image 提出双阶段合成监督与多视图一致性自监督方法以解决动物3D重建问题 3D reconstruction ✅
6 PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF 提出PIE-NeRF以解决高质量弹性动力学模拟问题 NeRF ✅
7 WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space 提出WildFusion以解决野外数据集中的3D图像合成问题 monocular depth ✅
8 Retargeting Visual Data with Deformation Fields 提出基于变形场的视觉数据重定向方法以解决现有编辑局限 neural radiance field
9 Unified Domain Adaptive Semantic Segmentation 提出统一领域自适应语义分割方法以解决图像与视频的知识转移问题 optical flow ✅
10 Boosting3D: High-Fidelity Image-to-3D by Boosting 2D Diffusion Prior to 3D Prior with Progressive Learning 提出Boosting3D以解决单图像引导3D生成中的视图一致性问题 NeRF
11 Differentiable Radio Frequency Ray Tracing for Millimeter-Wave Sensing 提出DiffSBR框架以解决毫米波传感中的3D重建问题 3D reconstruction
12 Test-Time Augmentation for 3D Point Cloud Classification and Segmentation 提出测试时增强方法以提升3D点云分类与分割性能 implicit representation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
13 Soulstyler: Using Large Language Model to Guide Image Style Transfer for Target Object 提出Soulstyler以解决图像风格转移中目标对象个性化的问题 large language model ✅
14 Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs 提出TGDoc以解决文本丰富场景下文档理解问题 large language model multimodal instruction following
15 HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data 提出HalluciDoctor以解决视觉指令数据中的幻觉毒性问题 large language model instruction following ✅
16 Visual In-Context Prompting 提出通用视觉上下文提示框架以解决视觉任务问题 large language model ✅
17 Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation 提出快速-慢速测试时适应方法以解决在线视觉-语言导航问题 VLN ✅
18 Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer 提出E$^2$STR以解决场景文本识别中的领域变化问题 large language model ✅

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

#题目一句话要点标签🔗⭐
19 LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes 提出LucidDreamer以解决3D场景生成领域的域限制问题 dreamer 3D gaussian splatting gaussian splatting
20 ADriver-I: A General World Model for Autonomous Driving 提出ADriver-I以解决自主驾驶中的模块冗余问题 world model world models large language model
21 EA-KD: Entropy-based Adaptive Knowledge Distillation 提出EA-KD以解决知识蒸馏中样本价值不均的问题 distillation large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 XAGen: 3D Expressive Human Avatars Generation 提出XAGen以解决3D人类虚拟形象表达控制不足的问题 manipulation ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页