cs.CV（2023-10-10）

📊 共 12 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization	提出利用神经辐射场提升视觉定位的不确定性感知	NeRF neural radiance field
2	High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field	提出空间变化表情条件神经辐射场以解决3D头像重建中的细节保留问题	NeRF neural radiance field
3	SketchBodyNet: A Sketch-Driven Multi-faceted Decoder Network for 3D Human Reconstruction	提出SketchBodyNet以解决从自由手绘草图重建3D人形的问题	3D reconstruction SMPL
4	TextPSG: Panoptic Scene Graph Generation from Textual Descriptions	提出TextPSG以解决从文本描述生成全景场景图的问题	scene understanding	✅

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

#	题目	一句话要点	标签	🔗	⭐
5	CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding	提出CoT3DRef以解决3D视觉定位中的可解释性与数据效率问题	visual grounding chain-of-thought
6	Uni3D: Exploring Unified 3D Representation at Scale	提出Uni3D以解决3D对象和场景统一表示的挑战	foundation model
7	On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets	提出VLIT数据集评估与优化方法以提升多模态指令调优模型性能	multimodal

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

#	题目	一句话要点	标签	🔗	⭐
8	Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Images	提出自监督基础模型以解决医学病理数据稀缺问题	masked autoencoder MAE foundation model
9	Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality	提出渐进式数据蒸馏以提升深度网络训练性能	distillation
10	Distillation Improves Visual Place Recognition for Low Quality Images	提出知识蒸馏方法以提升低质量图像的视觉位置识别	distillation

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models	提出一种新方法以实现开放词汇的视频目标跟踪	manipulation scene understanding open-vocabulary
12	Perceptual MAE for Image Manipulation Localization: A High-level Vision Learner Focusing on Low-level Features	提出感知MAE以解决图像篡改定位问题	manipulation masked autoencoder MAE

⬅️ 返回 cs.CV 首页 · 🏠 返回主页