🔳 SOTA Semantic Boundary 🔳

👉Mobile-Seed, a lightweight, dual-task framework tailored for simultaneous semantic segmentation and boundary detection.

👉Review https://t.ly/GsArZ
👉Project whu-usi3dv.github.io/Mobile-Seed/
👉Paper arxiv.org/pdf/2311.12651.pdf
👉Code github.com/WHU-USI3DV/Mobile-Seed

🧿 SOTA Model-aware 3D Gaze 🧿

👉 Novel hybrid approach that outputs 3D eye model, semantic segmentation, cam-intrinsic & pose. Only 2D eye semantic segmentation masks and fewer 3D gaze labels for supervision.

👉Review https://t.ly/AdKRf
👉Paper https://lnkd.in/dWb9GHPh
👉Code https://lnkd.in/dfAWFVky

🦖T-Rex: Counting by Visual Prompting🦖

👉T-Rex: a novel interactive object counting model to detect and count any objects. Impressive results!

👉Review https://t.ly/4SfFX
👉Project https://lnkd.in/dVtEndHv
👉Paper https://lnkd.in/dBGQsbdP
👉Code (not announced, but an empty repo exists): https://lnkd.in/dnZnGRUn

🔥 Stable (Stability.AI) Video Diffusion 🔥

👉 #StabilityAI released Stable Video Diffusion: latent video diffusion model for high-resolution, SOTA text-to-video and image-to-video generation

👉 Review https://t.ly/XwHys
👉 Code https://lnkd.in/dQw_yNuV
👉 Paper https://lnkd.in/dHn6f787

🎡 Panoptic Video Scene Graph 🎡

👉Combining video scene graph generation w/ panoptic segmentation for holistic video understanding. Novel HQ dataset with fine, temporal scene graph annotations & panoptic segmentation. Code released!🔥

👉Review https://t.ly/tckDT
👉Project jingkang50.github.io/PVSG/
👉Paper arxiv.org/pdf/2311.17058.pdf
👉Code github.com/LilyDaytoy/OpenPVSG
👉Tool github.com/lilyDaytoy/PVSGAnnotation

🌳 NebulOS: (more than) Green AI 🌳

👉A novel hardware-aware Training-Free NAS approach that considers both training-free metrics & HW constraints, aiming to find the optimal balance between validation accuracy & energy consumption. 🚀

👉Review https://t.ly/Ozso1
👉Project sites.google.com/view/nebulos
👉Code github.com/fracapuano/NebulOS
👉Video https://lnkd.in/exN4Q2Fu
👉Hugging Face https://lnkd.in/eyCcPEPc

🧱 Material Palette from Images 🧱

👉A novel problem in #AI: material extraction from a real-world image without any prior knowledge 🤯

👉Discussion https://t.ly/AIWs-
👉Paper https://lnkd.in/dBFAVWPF
👉Project https://lnkd.in/dV5jK8Sm
👉Code https://lnkd.in/dNhMnfFb
👉Dataset (coming) ...

👑 HD Generative #AI With No $$👑

👉DemoFusion: a novel approach for HD image generation w/ no money. Progressive Upscaling, Skip Residual, & Dilated Sampling to achieve higher-resolution ever 🔥

👉Review https://t.ly/sIqDV
👉Paper https://lnkd.in/deDt-zcK
👉Project https://lnkd.in/dFGj47Xw
👉Code https://lnkd.in/dY3UcXwp

🍡 Animate Anyone: new SOTA! 🍡

👉Alibaba unveils Animate Anyone: novel #AI for transforming character images into animated videos controlled by desired pose sequences. Animating any character image into a video, unconstrained by specific domains 🚀

👉Review https://t.ly/qCahZ
👉Paper https://lnkd.in/d-zi8EZ6
👉Project https://lnkd.in/djwjQRvq
👉Repo https://lnkd.in/dDMkjnKz

🔎 Generative Powers of Ten 🔍

👉A text-to-image model to generate consistent content across multiple image scales, enabling extreme semantic zooms into a scene. From universe to a human cell 🤯

👉Review https://t.ly/2DG44
👉Paper https://lnkd.in/eDcSpU59
👉Project https://lnkd.in/e6NKu8n9

Hello everybody,
a lot of you asked me to re-open the sharing of the contents to involve more people. I want to follow your suggestion, hope you will enjoy this new mood!

👍 FREE TO FORWARD TO OTHER TELEGRAM CHANNELS

🔥 NO COPY OF THE POSTS
🔥 NO COMMERCIAL USAGE
🔥 NO UNRESPECTFUL USAGE

⚠️ UNDO THE FORWARDING OPTION AT THE FIRST VIOLATION ⚠️

🩰 Magic Animating Human 🩰

👉MagicAnimate: the new SOTA in human animation. Code available: let's dance!

👉Review https://t.ly/Oq7Za
👉Paper https://lnkd.in/dSUbGgCs
👉Project https://lnkd.in/dkVFf-SV
👉Code https://lnkd.in/dj2dbzdg
👉Demo https://lnkd.in/dHEKPE9q

🔥 EfficientSAM: 20x faster Segment Anything 🔥

👉Meta AI Research unveils a novel family of SAM-like models, light-weight SAM models with SOTA quality-efficiency trade-offs. Up to 20x faster!

👉Review https://t.ly/966QS
👉Paper https://lnkd.in/duijp_Rh
👉Project https://lnkd.in/dW-p2CuH
👉Code https://lnkd.in/dAbZaB2t
👉Demo https://lnkd.in/d-tjKiUd

🫶3D Hands with Transformers🫶

👉 HaMeR is a robust and accurate Hand Mesh Recovery from images and video frames, based on Transformer architecture. It's the new SOTA.

👉Review https://t.ly/YtAW8
👉Paper https://arxiv.org/pdf/2312.05251.pdf
👉Project https://geopavlakos.github.io/hamer
👉Demo huggingface.co/spaces/geopavlakos/HaMeR
👉Colab colab.research.google.com/drive/1rQbQzegFWGVOm1n1d-S6koOWDo7F2ucu

🪩 DreaMoving: Human Dancer 🪩

👉Alibaba strikes again with DreaMoving: a diffusion-based controllable video generation framework to produce HQ customized human videos.

👉Review https://t.ly/BD_Yf
👉Paper https://lnkd.in/gepP6Rjw
👉Project https://lnkd.in/gwm72cfS
👉Repo (empty) https://lnkd.in/gsc2Qt-F

📲 EdgeSAM: Mobile 40x SAM 📲

👉A novel hyper-optimized version of SAM for mobile devices such as #Iphone. Pure CNNs backbone (better suitable for ANE), up to 40x faster. Code available 😉

👉Review https://t.ly/m_vLH
👉Paper https://lnkd.in/gHZVZN2x
👉Project https://lnkd.in/gK8qEK8p
👉Repo https://lnkd.in/gj6YAGNv
👉Hugging Face https://lnkd.in/gUUHJvxz

🪼PatchFusion: SOTA Mono-Depth🪼

👉PatchFusion: novel end-to-end tile-based framework for hi-res monocular metric depth estimation. It's the new SOTA in metric depth estimation from mono. Code & Demo on Hugging Face able 🔥

👉Review https://t.ly/hv3yT
👉Paper https://lnkd.in/d9dXP7iP
👉Project https://lnkd.in/dQcvVJSx
👉Repo https://lnkd.in/dW2GdVR5
👉Demo https://lnkd.in/dFW-gAiY

💃Outfit Anyone: Ultra-HQ VTO💃

👉Alibaba unveils Outfit Anyone: a two-stream conditional diffusion able to adeptly handle garment deformation for more lifelike results in VOT. Extra: Outfit Anyone + Animate Anyone for outfit + motion generation of any character. NO CODE / NO PAPER / DEMO AVAILABLE :)

👉Review https://t.ly/o6UR9
👉Demo https://lnkd.in/dpQYdXhc
👉Repo (empty) https://lnkd.in/dBsNST6r

🔥 #AIwithPapers: we are 8k+ 🔥

👉 After flirting with #ChatGpt for months, you back in love with this channel. I felt bad, but I forgive you 🧡

😈 Hey Telegram Premium Subscribers, what about boosting us? Click: https://news.1rj.ru/str/AI_DeepLearning?boost

😈 Invite -> https://news.1rj.ru/str/AI_DeepLearning

🧊 Depth Conditioning 🧊

👉LooseControl to control the generative image modeling process. Layout by boundaries and #3D box control via object locations (approximate bounding boxes)

👉Review https://t.ly/9y72m
👉Paper https://arxiv.org/pdf/2312.03079.pdf
👉Project https://shariqfarooq123.github.io/loose-control/
👉Repo https://github.com/shariqfarooq123/LooseControl

🖲️ Amodal Tracking Any Object 🖲️

👉Amodal tracking": inferring complete object boundaries, even when certain portions are occluded. New benchmark & approach, 2x better than SOTA in people tracking 🔥

👉Review https://t.ly/Rc6Ku
👉Paper https://lnkd.in/d39rFYT4
👉Project https://lnkd.in/d7bkEcni
👉(empty) Repo https://lnkd.in/dTsNKdfz