Available now! Telegram Research 2025 — the year's key insights 
AI with Papers - Artificial Intelligence & Deep Learning
Open in Telegram
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
Show more📈 Analytical overview of Telegram channel AI with Papers - Artificial Intelligence & Deep Learning
Channel AI with Papers - Artificial Intelligence & Deep Learning (@ai_deeplearning) in the English language segment is an active participant. Currently, the community unites 17 144 subscribers, ranking 7 701 in the Technologies & Applications category and 2 225 in the Malaysia region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 17 144 subscribers.
According to the latest data from 25 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by -186 over the last 30 days and by 3 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 23.94%. Within the first 24 hours after publication, content typically collects 6.86% reactions from the total number of subscribers.
- Post reach: On average, each post receives 0 views. Within the first day, a publication typically gains 1 177 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 0.
- Thematic interests: Content is focused on key topics such as framework, object, dataset, tba, depth.
📝 Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
“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”
Thanks to the high frequency of updates (latest data received on 26 June, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Technologies & Applications category.
17 144
Subscribers
+324 hours
-367 days
-18630 days
Posts Archive
🌪️ TimeLapse++: Video Temporal Pyramid🌪️
👉Multi-scale lens to view the passage of time: far beyond a "classic" timelapse
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Inspired by "old-school" spatial pyramids
✅Video Spectrogram to go through pyramid
✅Months/years of data in a few seconds!
✅Multi-temporal freq., no aliasing
More: https://bit.ly/3TKnYPS
🥑 DALL·E: Outpainting via #NLP 🥑
👉Extending any original image, creating large-scale images in any aspect ratio
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Extending an image beyond its borders
✅Visual elements in same style of the input
✅Driving the image "story" in new directions
✅Shadows, reflections & textures w/ context
More: https://bit.ly/3eoH8uD
🪨Controllable #3D Adversarial Face🪨
👉#Meta (+CMU) on decoupling identity/expression + granular control over expressions
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Supervised auto-enc. + GAN
✅UV texture maps + 3D faces
✅Control expression, saving ID
✅Code under X11 License
More: https://bit.ly/3AVE80q
🚗 Massive Dataset in Virtual Cities 🚗
👉Synthehicle: 7 hours of labeled material, 340 cams, 64 days, rain, dawn, & night scenes.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Multi-target multi-cam tracking
✅2D, 3D, segm. & depth annotations
✅Instance, semantic & panoptic segm.
✅340 clips, 64 scenes, 17 hrs, 4M BBs
More: https://bit.ly/3TArHiV
🧡 Avatarization in 90's. So Romantic 🧡
👉Making of the first #MortalKombat in early 90's
More: https://bit.ly/3wTSpJB
🍊StableFace: Talking Face Generation🍊
👉Analysis on motion jittering in 3D face generation (audio-in -> video-out)
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Motion jittering analysis for stability
✅Gaussian-based adaptive smoothing
✅Augmented erosions of neural renderer
✅Audio-fused generator for dependency
More: https://bit.ly/3Kt95gI
🎍#3D scene manipulation from 2D🎍
👉Reconstruct, decompose, manipulate & render 3D scenes in a single pipeline
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Unique 3D, non-occupied space from 2D
✅Inverse query algorithm for shapes
✅First synthetic dataset for 3D editing
More: https://bit.ly/3RlYhTY
🔵 Deep Saliency: driving the attention 🔵
👉Google unveils a family of operators to "drive" human saliency
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Editing image to drive Saliency
✅Transforms to hide distractors
✅Warping operator for distractor
✅GAN-op for less-saliency altern.
More: https://bit.ly/3KoQQc2
🔥 #AIwithPapers: we are 4,000+! 🔥
💙💛Lot of people joined, and we talked about #StableDiffusion only twice! Can't believe it.💙💛
😈 Invite your friends -> https://t.me/AI_DeepLearning
🔥IDOL (#CVPR2022 winner): code is out!🔥
👉IDOL for VIS: outperforming all online/offline methods, the new SOTA!
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Online usually inferior by >10AP
✅Online based on contrast-learning
✅Discriminative++ instance embeddings
✅Full exploiting history for stability
More https://bit.ly/3dXCDXw
🦉PANDORA: Polarized Neural Decomposition🦉
👉CIL lab unveils PANDORA: polarimetric inverse rendering approach via INR
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Geometry, reflectance & illumination
✅normal, signed distance field, mesh
✅Diffuse-specular separation
✅Hi-fI incident illumination
More https://bit.ly/3CzGp3F
🍈 #StableDiffusion archive is out🍈
👉Lexica art is a Stable Diffusion prompt search engine. Real-time, countless #stablediffusion results for everyone. I had fun with the GOAT, #Maradona.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Maradona scoring against a capybara...
✅A poster of space jam with Maradona...
✅Painting of Maradona very detailed...
✅Painting of Maradona in heaven...
More: https://bit.ly/3PTXHLH
🌐RelPose: Probabilistic Relative Pose🌐
👉A novel method for core component in #SLAM / NeRF-powered apps.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Core component of SfM/SLAM
✅Pre-processing for neural (NeRF)
✅Energy-based over rotations
✅SOTA on both seen/unseen objects
More: https://bit.ly/3T60TXw
🍈DeepBillboards: old-school trick for #VR🍈
👉DeepBillboards models a 3D object implicitly using neural net on the user’s viewing direction
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅#Google Brain +Tsukuba + Tokyo
✅Rendering at higher res., improving #VR
✅NeRF into interactive VR with accuracy++
✅NeRF (or any others) directly in #Unity
More: https://bit.ly/3CsTQ5y
🥭Massive GTA-V human dataset🥭
👉GTA-Human: outperforming SOTA with a purely synthetic training.
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅600+ gender, age, ethnicity & clothing
✅20,000+ clips, variety of human activities
✅6 categories of location, different BGs
✅Occlusions, lighting, and weather system
More: https://bit.ly/3wpZyRD
🔥 KeypointNeRF: code is out! 🔥
👉KeypointNeRF by #Meta: "NeRF"-avatars
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Generalizable NeRF for virtual avatar
✅Sparse 3D keypoints for SOTA avatar
✅Novel unseen subjects from 2/3 views
✅"iPhone" captures for #metaverse
More: https://bit.ly/3pyl17e
🔥🔥UPDATE🔥🔥
Code Released: https://github.com/facebookresearch/KeypointNeRF
🥑 CLIP-based Neural Style Transfer 🥑
👉From #Nvidia a novel method for transferring the style to a #3D object
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Texture style for 3D by CLIP-ResNet50
✅Nearest-neighbor feature matching loss
✅CLIP-based loss extraction of textures
✅NNFM for multiple style pics / control
✅No source code or models available 😒
More: https://bit.ly/3c32dK5
🍏NeuMan: Human NeRF in the wild🍏
👉#Apple opens a novel human pose/view from just a single in-the-wild video
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅No extra devices/annotations
✅Both Human (novel poses) + Scene
✅E2E SMPL optimization + error-corr.
✅Applications such as "telegathering"
More: https://bit.ly/3K4iTO6
🧰 FGT: flow-guided inpainting 🧰
👉#Microsoft (+USTC) unveils FGT: flow-guided ViT for video inpainting 🤯
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅OF into transformer for attention++
✅Flow completion net w/ local feats.
✅Dual perspective spatial MHSA
✅Local attention with global content
More: https://bit.ly/3pk5J5S
