AI with Papers - Artificial Intelligence & Deep Learning
Kanalga Telegram’da o‘tish
All the AI with papers. Every day fresh updates about #DeepLearning #MachineLearning #LLM & #ComputerVision Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/ #AI #chatGPT
Ko'proq ko'rsatish📈 Telegram kanali AI with Papers - Artificial Intelligence & Deep Learning analitikasi
AI with Papers - Artificial Intelligence & Deep Learning (@ai_deeplearning) Ingliz til segmentidagi kanali faol ishtirokchi. Hozirda hamjamiyat 17 058 obunachidan iborat bo'lib, Texnologiyalar & Aralashmalar toifasida 7 639-o'rinni va Malayziya mintaqasida 2 196-o'rinni egallagan.
📊 Auditoriya ko‘rsatkichlari va dinamika
невідомо sanasidan buyon loyiha tez o‘sib, 17 058 obunachiga ega bo‘ldi.
12 Iyul, 2026 dagi oxirgi ma’lumotlarga ko‘ra kanal barqaror faollikka ega. Oxirgi 30 kunda obunachilar soni -149 ga, so‘nggi 24 soatda esa 9 ga o‘zgardi va umumiy qamrov yuqori darajada qolmoqda.
- Tasdiqlash holati: Tasdiqlanmagan
- Jalb etish (ER): Auditoriya o‘rtacha 17.34% darajada jalb etiladi. Nashrdan keyingi dastlabki 24 soatda kontent odatda umumiy obunachilar sonining 7.54% ini tashkil etuvchi reaksiyalarni to‘playdi.
- Post qamrovi: Har bir post o‘rtacha 2 958 marta ko‘riladi; birinchi sutkada odatda 1 287 ta ko‘rish yig‘iladi.
- Reaksiyalar va o‘zaro ta’sir: Auditoriya faol: har bir postga o‘rtacha 15 ta reaksiya keladi.
- Tematik yo‘nalishlar: Kontent framework, object, dataset, tba, depth kabi asosiy mavzularga jamlangan.
📝 Tavsif va kontent siyosati
Muallif resursni shaxsiy fikrni ifoda etish maydoni sifatida ta’riflaydi:
“All the AI with papers. Every day fresh updates about #DeepLearning #MachineLearning #LLM & #ComputerVision
Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/
#AI #chatGPT”
Yuqori yangilanish chastotasi (oxirgi ma’lumot 13 Iyul, 2026 da olingan) sababli kanal doimo dolzarb va katta qamrovli bo‘lib qoladi. Analitika auditoriya kontent bilan faol hamkorlik qilishini, uni Texnologiyalar & Aralashmalar toifasidagi muhim ta’sir nuqtasiga aylantirishini ko‘rsatadi.
17 058
Obunachilar
+924 soatlar
-357 kunlar
-14930 kunlar
Postlar arxiv
🔥 Depth Anything v2 is out! 🔥
👉 Depth Anything V2: outperforming V1 in robustness and fine-grained details. Trained from 595K synthetic labeled images and 62M+ real unlabeled images, the new SOTA in monocular depth estimation (MDE). Code & Models available💙
👉Review https://t.ly/QX9Nu
👉Paper arxiv.org/pdf/2406.09414
👉Project depth-anything-v2.github.io/
👉Repo github.com/DepthAnything/Depth-Anything-V2
👉Data huggingface.co/datasets/depth-anything/DA-2K
🌾 LLaNA: a NeRF-LLM assistant 🌾
👉UniBO unveils LLaNA; novel Multimodal-LLM that understands and reasons on an input NeRF. It processes directly the NeRF weights and performs tasks such as captioning, Q&A, & zero-shot classification of NeRFs.
👉Review https://t.ly/JAfhV
👉Paper arxiv.org/pdf/2406.11840
👉Project andreamaduzzi.github.io/llana/
👉Code & Data coming
🌮 MeshAnything with Transformers 🌮
👉MeshAnything converts any 3D representation into Artist-Created Meshes (AMs), i.e., meshes created by human artists. It can be combined with various 3D asset production pipelines, such as 3D reconstruction and generation, to transform their results into AMs that can be seamlessly applied in the 3D industry. Source Code available💙
#artificialintelligence #machinelearning #ml #AI #deeplearning #computervision #AIwithPapers #metaverse
👉Review https://t.ly/HvkD4
👉Paper arxiv.org/pdf/2406.10163
👉Code github.com/buaacyw/MeshAnythinghttps://t.ly/HvkD4
🍦Geometry Guided Depth Estimation🍦
👉A novel system for depth estimation and #3D reconstruction which can take as input, where available, previously-made estimates of the scene’s geometry
👉Review https://lnkd.in/dMgakzWm
👉Paper https://arxiv.org/pdf/2406.18387
👉Repo (empty) https://github.com/nianticlabs/DoubleTake
🍦Geometry Guided Depth Estimation🍦
👉#Niantic (+ULC) unveils a novel system for depth estimation and #3D reconstruction which can take as input, where available, previously-made estimates of the scene’s geometry. Source Code announced💙
👉Review https://lnkd.in/dMgakzWm
👉Paper https://arxiv.org/pdf/2406.18387
👉Repo (empty) https://github.com/nianticlabs/DoubleTake
🐻StableNormal: Stable/Sharp Normal🐻
👉Alibaba unveils StableNormal, a novel method which tailors the diffusion priors for monocular normal estimation. Hugging Face demo is available💙
👉Review https://t.ly/FPJlG
👉Paper https://arxiv.org/pdf/2406.16864
👉Demo https://huggingface.co/Stable-X
🧬 Event-driven SuperResolution 🧬
👉USTC unveils EvTexture, the first VSR method that utilizes event signals for texture enhancement. It leverages high-frequency details of events to better recover texture regions in VSR. Source Code available💙
👉Review https://t.ly/zlb4c
👉Paper arxiv.org/pdf/2406.13457
👉Code github.com/DachunKai/EvTexture
🤓 Glasses-Removal from Videos🤓
👉Lightricks unveils a novel method able to receive an input video of a person wearing glasses, and consistently removes the glasses, while preserving the ID. It works even when there are reflections, heavy makeup, and eye blinks. Code announced, not yet released💙
👉Review https://t.ly/Hgs2d
👉Paper arxiv.org/pdf/2406.14510
👉Project https://v-lasik.github.io/
👉Code github.com/v-lasik/v-lasik-code
🌱 TokenHMR : new 3D human pose SOTA 🌱
👉TokenHMR is the new SOTA HPS method mixing 2D keypoints and 3D pose accuracy, thus leveraging Internet data without known camera parameters. It's the new SOTA by a large margin.
👉Review https://t.ly/K9_8n
👉Paper arxiv.org/pdf/2404.16752
👉Project tokenhmr.is.tue.mpg.de/
👉Code github.com/saidwivedi/TokenHMR
💦 Self-driving in wet conditions 💦
👉BMW SemanticSpray: novel dataset contains scenes in wet surface conditions captured by camera, LiDAR and radar. Camera: 2D Boxes | LiDAR: 3D Boxes, Semantic Labels | Radar: Semantic Labels.
👉Review https://t.ly/8S93j
👉Paper https://lnkd.in/dnN5MCZC
👉Project https://lnkd.in/dkUaxyEF
👉Data https://lnkd.in/ddhkyXv8
🧤HOT3D Hand/Object Tracking🧤
👉#Meta opens a novel egocentric dataset for 3D hand & object tracking. A new benchmark for vision-based understanding of 3D hand-object interactions. Dataset available 💙
👉Review https://t.ly/cD76F
👉Paper https://lnkd.in/e6_7UNny
👉Data https://lnkd.in/e6P-sQFK
🌵 RobustSAM for Degraded Images 🌵
👉RobustSAM, the evolution of SAM for degraded images; enhancing the SAM’s performance on low-quality images while preserving prompt-ability & zeroshot generalization. Dataset & Source Code released💙
👉Review https://t.ly/mnyyG
👉Paper arxiv.org/pdf/2406.09627
👉Project robustsam.github.io
👉Code github.com/robustsam/RobustSAM
📫 MeshPose: DensePose + HMR 📫
👉MeshPose: novel approach to jointly tackle DensePose and Human Mesh Reconstruction in a while. A natural fit for #AR applications requiring real-time mobile inference.
👉Review https://t.ly/a-5uN
👉Paper https://arxiv.org/pdf/2406.10180
👉Project https://meshpose.github.io/
🎹 PianoMotion10M for gen-hands 🎹
👉PianoMotion10M: 116 hours of piano playing videos from a bird’s-eye view with 10M+ annotated hand poses. A big contributions in hand motion generation. Code & Dataset released💙
👉Review https://t.ly/_pKKz
👉Paper arxiv.org/pdf/2406.09326
👉Code https://lnkd.in/dcBP6nvm
👉Project https://lnkd.in/d_YqZk8x
👉Dataset https://lnkd.in/dUPyfNDA
🍉 MASA: MOT Anything By SAM 🍉
👉MASA: Matching Anything by Segmenting Anything pipeline to learn object-level associations from unlabeled images of any domain. An universal instance appearance model for matching any objects in any domain. Source code in June 💙
👉Review https://t.ly/pKdEV
👉Paper https://lnkd.in/dnjuT7xm
👉Project https://lnkd.in/dYbWzG4E
👉Code https://lnkd.in/dr5BJCXm
👑 Kling AI vs. OpenAI Sora 👑
👉Kling: the ultimate Chinese text-to-video model - rival to #OpenAI’s Sora. No papers or tech info to check, but stunning results from the official site.
👉Review https://t.ly/870DQ
👉Paper ???
👉Project https://kling.kuaishou.com/
👗 SOTA Multi-Garment VTOn Editing 👗
👉#Google (+UWA) unveils M&M VTO, novel mix 'n' match virtual try-on that takes as input multiple garment images, text description for garment layout and an image of a person. It's the new SOTA both qualitatively and quantitatively. Impressive results!
👉Review https://t.ly/66mLN
👉Paper arxiv.org/pdf/2406.04542
👉Project https://mmvto.github.io
🧊 Universal 6D Pose/Tracking 🧊
👉Omni6DPose is a novel dataset for 6D Object Pose with 1.5M+ annotations. Extra: GenPose++, the novel SOTA in category-level 6D estimation/tracking thanks to two pivotal improvements.
👉Review https://t.ly/Ywgl1
👉Paper arxiv.org/pdf/2406.04316
👉Project https://lnkd.in/dHBvenhX
👉Lib https://lnkd.in/d8Yc-KFh
🚙 UA-Track: Uncertainty-Aware MOT🚙
👉UA-Track: novel Uncertainty-Aware 3D MOT framework which tackles the uncertainty problem from multiple aspects. Code announced, not released yet.
👉Review https://t.ly/RmVSV
👉Paper https://arxiv.org/pdf/2406.02147
👉Project https://liautoad.github.io/ua-track-website
📞FacET: VideoCall Change Your Expression📞
👉Columbia University unveils FacET: discovering behavioral differences between conversing face-to-face (F2F) and on video-calls (VCs).
👉Review https://t.ly/qsQmt
👉Paper arxiv.org/pdf/2406.00955
👉Project facet.cs.columbia.edu/
👉Repo (empty) github.com/stellargo/facet
