cs.CV（2024-03-21）

📊 共 39 篇论文 | 🔗 11 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (19 🔗7) 支柱九：具身大模型 (Embodied Foundation Models) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (3) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (19 篇)

#题目一句话要点标签🔗⭐
1 HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression 提出HAC框架以解决3D高斯点云压缩问题 3D gaussian splatting 3DGS gaussian splatting ✅
2 MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images 提出MVSplat以解决稀疏多视图图像的3D高斯建模问题 3D gaussian splatting gaussian splatting splatting
3 Isotropic Gaussian Splatting for Real-Time Radiance Field Rendering 提出各向同性高斯点云以解决计算复杂性问题 3D gaussian splatting 3D reconstruction gaussian splatting
4 Hyperspectral Neural Radiance Fields 提出超光谱神经辐射场以解决3D重建中的光谱信息缺失问题 3D reconstruction NeRF neural radiance field
5 Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection 提出无解码器架构以解决开放词汇视觉关系检测问题 open-vocabulary open vocabulary
6 Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models 提出开放词汇注意力图以解决语义分割问题 open-vocabulary open vocabulary
7 Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions 提出Thermal-NeRF以解决低光照条件下重建问题 3D reconstruction NeRF neural radiance field
8 CombiNeRF: A Combination of Regularization Techniques for Few-Shot Neural Radiance Field View Synthesis 提出CombiNeRF以解决少量视图合成中的过拟合问题 NeRF neural radiance field
9 InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity 提出InfNeRF以实现无限规模NeRF渲染 NeRF neural radiance field
10 SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field 提出SurroundSDF以解决3D场景理解中的障碍表面构建问题 scene reconstruction scene understanding
11 Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians 提出Mini-Splatting以解决高效场景表示问题 gaussian splatting splatting ✅
12 Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance 提出基于3D参数模型的可控一致人像动画方法 semantic map motion latent SMPL ✅
13 GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation 提出GRM以解决稀疏视图下3D重建效率低的问题 3D reconstruction ✅
14 Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering 提出Gaussian Frosting以实现实时复杂3D效果的高质量渲染与编辑 3D gaussian splatting gaussian splatting splatting ✅
15 CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers 提出CathFlow以解决介入超声中导管分割问题 optical flow
16 Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation 提出Zero123-6D以解决RGB类别级6D姿态估计问题 6D pose estimation
17 PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model 提出PSALM以解决图像分割任务中的多模态挑战 open-vocabulary open vocabulary ✅
18 ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decomposition 提出ClusteringSDF以解决3D分解与重建问题 NeRF
19 3D Object Detection from Point Cloud via Voting Step Diffusion 提出投票步骤扩散方法以解决3D物体检测中的噪声问题 scene understanding ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
20 Empowering Segmentation Ability to Multi-modal Large Language Models 提出LLaVASeg以解决多模态大语言模型的分割能力不足问题 large language model chain-of-thought ✅
21 Multimodal-Conditioned Latent Diffusion Models for Fashion Image Editing 提出多模态条件潜在扩散模型以解决时尚图像编辑问题 multimodal
22 Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering 提出多代理系统以解决视觉问答中的零-shot能力问题 foundation model
23 VidLA: Video-Language Alignment at Scale 提出VidLA以解决视频语言对齐的规模化问题 foundation model visual grounding
24 MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? 提出MathVerse基准以评估多模态大语言模型在视觉数学问题中的能力 large language model chain-of-thought
25 Few-Shot Adversarial Prompt Learning on Vision-Language Models 提出少样本对抗提示学习框架以提升视觉语言模型的对抗鲁棒性 foundation model ✅
26 VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding 提出VURF框架以提升视频理解与推理能力 large language model
27 Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination 提出Pensieve以解决多模态大语言模型的视觉幻觉问题 large language model
28 Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semantics 提出Meta Domain Alignment Semantic Refinement以解决跨域零-shot学习问题 large language model
29 OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation 提出OTSeg以解决零-shot语义分割中的多模态知识对齐问题 multimodal

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

#题目一句话要点标签🔗⭐
30 Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference 提出Cobra以解决多模态大语言模型的计算效率问题 Mamba spatial relationship large language model
31 Learning to Project for Cross-Task Knowledge Distillation 提出反向投影以解决跨任务知识蒸馏问题 distillation depth estimation
32 Unsupervised Audio-Visual Segmentation with Modality Alignment 提出无监督音视频分割方法以解决昂贵标注问题 contrastive learning foundation model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
33 Exploring 3D Human Pose Estimation and Forecasting from the Robot's Perspective: The HARPER Dataset 提出HARPER数据集以解决机器人视角下的3D人体姿态估计问题 quadruped dyadic interaction
34 On the exploitation of DCT statistics for cropping detectors 提出基于DCT统计的图像裁剪检测方法以解决图像分辨率识别问题 manipulation
35 ReNoise: Real Image Inversion Through Iterative Noising 提出ReNoise以解决真实图像反演问题 manipulation

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
36 VibNet: Vibration-Boosted Needle Detection in Ultrasound Images 提出VibNet以解决超声图像中针头检测难题 spatiotemporal ✅
37 EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition 提出EventDance以解决无标签源数据的跨模态适应问题 spatiotemporal

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

#题目一句话要点标签🔗⭐
38 Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Consideration 提出一种考虑不确定性的3D人类动作预测方法以解决动态复杂性问题 human motion human motion prediction motion prediction ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
39 Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition 提出内容-帧运动潜在分解模型以解决视频生成效率问题 motion latent

⬅️ 返回 cs.CV 首页 · 🏠 返回主页