Artificial Intelligence l l AI Updates
前往频道在 Telegram
1 615
订阅者
+124 小时
+27 天
+430 天
帖子存档
🔗 GitHub_Link
❇️ Adversarial Diffusion Distillation 🔥
#DiffusionModels
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ Re-implementation of Adversarial Diffusion Distillation by AMD 🔥
#DiffusionModels
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ EasyVolcap: Accelerating Neural Volumetric Video Research 🔥
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ Test-Time Optimization for Video Depth Estimation Using Pseudo Reference Depth
#DepthEstimation
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
#GAN
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ Kiuikit is one of the toolkits for computer vision (especially 3D vision) tasks.
#3D
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ L4GM: Large 4D Gaussian Reconstruction Model
#4D
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists 🔥
#Text2Img
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ Motion Prompting: Controlling Video Generation with Motion Trajectories 🔥
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction 🔥
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ Depth-pro-pointcloud 🔥
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting
#3D #GaussianSplatting
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ PuzzleAvatar: Assembly of Avatar from Unconstrained Photo Collections
#3D
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ RollingDepth: Video Depth without Video Models
#DepthEstimation
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ FlipSketch: Flipping assets Drawings to Text-Guided Sketch Animations 🔥🚀
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ ZIM: Zero-Shot Image Matting for Anything 🔥
#SAM
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
#YOLO #DocumentLayoutAnalysis
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ YOLO models trained by DocLayNet - power your Document Intelligent by Layout Analysis
#YOLO
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks 🔥📝🔥
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
🔗 GitHub_Link
❇️ UVDoc: Neural Grid-based Document Unwarping 🔥📝🔥
Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates
现已上线!2025 年 Telegram 研究 — 年度关键洞察 
