cs.CV（2023-11-27）

📊 共 37 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗3) 支柱四：生成式动作 (Generative Motion) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Where to Begin? From Random to Foundation Model Instructed Initialization in Federated Learning for Medical Image Segmentation 提出基础模型指导初始化以解决联邦学习中的医学图像分割问题 foundation model
2 Compositional Chain-of-Thought Prompting for Large Multimodal Models 提出组合链式思维提示以解决多模态模型的视觉推理问题 large language model multimodal chain-of-thought ✅
3 LLMGA: Multimodal Large Language Model based Generation Assistant 提出LLMGA以提升图像生成与编辑的精确性 large language model multimodal
4 ChartLlama: A Multimodal LLM for Chart Understanding and Generation 提出ChartLlama以解决图表理解与生成问题 large language model multimodal
5 Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models 提出Video-Bench以评估视频基础的大型语言模型 large language model ✅
6 End-to-End Breast Cancer Radiotherapy Planning via LMMs with Consistency Embedding 提出RO-LMM以优化放射肿瘤学中的治疗计划 foundation model multimodal
7 RelVAE: Generative Pretraining for few-shot Visual Relationship Detection 提出RelVAE以解决少样本视觉关系检测问题 multimodal
8 VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation 提出VLPrompt以解决全景场景图生成中的长尾关系问题 large language model ✅
9 EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension 提出EVCap以解决开放世界理解中的对象知识更新问题 large language model
10 FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax 提出FlowZero以解决零样本文本到视频合成问题 large language model
11 SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation 提出SAM-6D以解决零-shot 6D物体姿态估计问题 zero-shot transfer
12 ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models 提出属性引导的提示调优方法以解决视觉-语言模型的分布转移问题 large language model
13 MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers 提出MeshGPT以生成紧凑的三角网格 large language model

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

#题目一句话要点标签🔗⭐
14 Mip-Splatting: Alias-free 3D Gaussian Splatting 提出3D平滑滤波器以解决3D高斯点云采样伪影问题 3D gaussian splatting gaussian splatting splatting
15 SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation 提出SED以解决开放词汇语义分割问题 open-vocabulary open vocabulary ✅
16 Animatable and Relightable Gaussians for High-fidelity Human Avatar Modeling 提出可动画和可重光照的高保真人体头像建模方法 3D gaussian splatting gaussian splatting splatting
17 SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields 提出SOAC以解决多传感器校准问题 NeRF neural radiance field
18 Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing 提出可重光照的3D高斯点云以解决真实感渲染问题 3D gaussian splatting gaussian splatting splatting
19 Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Maps 提出基于弱监督的3D重建方法以解决衣着人类建模问题 3D reconstruction
20 GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions 提出GaussianEditor以解决3D场景精细编辑问题 3D gaussian splatting gaussian splatting splatting
21 FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding 提出公平学习方法以解决持续语义场景理解中的公平性问题 scene understanding
22 InceptionHuman: Controllable Prompt-to-NeRF for Photorealistic 3D Human Generation 提出InceptionHuman以解决3D人类生成的多模态控制问题 NeRF
23 CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering 提出CaesarNeRF以解决神经辐射场的少样本泛化问题 NeRF neural radiance field
24 Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes 提出神经3D笔触技术以生成风格化3D场景图像 neural radiance field ✅
25 Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars 提出Animatable 3D Gaussian以解决多人体素重建问题 neural radiance field

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
26 Source-Free Domain Adaptation with Frozen Multimodal Foundation Model 提出DIFO方法以解决源无关领域适应问题 distillation foundation model multimodal
27 A-JEPA: Joint-Embedding Predictive Architecture Can Listen 提出A-JEPA以提升音频自监督学习效果 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
28 OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving 提出OccWorld以解决自动驾驶中3D场景理解问题 world model world models ✅
29 ViT-Lens: Towards Omni-modal Representations 提出ViT-Lens-2以解决多模态表示学习问题 representation learning foundation model multimodal ✅
30 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation 提出图像引导网络解决弱监督3D语义分割问题 contrastive learning distillation
31 EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth 提出EucliDreamer以解决3D模型纹理生成问题 dreamer distillation
32 Dataset Distillation in Latent Space 提出在潜在空间中进行数据集蒸馏以解决高复杂度问题 distillation
33 Efficient Dataset Distillation via Minimax Diffusion 提出最小最大扩散方法以高效蒸馏数据集 distillation ✅

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
34 InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint 提出InterControl以解决多人人体交互生成问题 motion diffusion model motion diffusion motion synthesis ✅
35 CG-HOI: Contact-Guided 3D Human-Object Interaction Generation 提出CG-HOI以解决动态3D人机交互生成问题 physically plausible human-object interaction HOI

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

#题目一句话要点标签🔗⭐
36 GART: Gaussian Articulated Template Models 提出GART模型以高效捕捉和渲染非刚性关节对象 SMPL

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
37 Real Time GAZED: Online Shot Selection and Editing of Virtual Cameras from Wide-Angle Monocular Video Recordings 提出Real Time GAZED以解决实时视频编辑与稳定性问题 trajectory optimization

⬅️ 返回 cs.CV 首页 · 🏠 返回主页