AI with Papers - Artificial Intelligence & Deep Learning

🍋‍🟩Remesh-Aware Mesh Deformation🍋‍🟩 👉RADmesh is a novel generative deformation technique enhanced by remeshing. Given a text prompt, it deforms and remeshes a mesh region to form new geometric features. Repo MIT💙 👉Review https://lnkd.in/p/eK6FZv9c 👉Paper https://arxiv.org/pdf/2608.17182 👉Project https://threedle.github.io/radmesh/ 👉Repo https://github.com/threedle/radmesh/

🐆 Anyone in 4D is out 🐆 👉4DAnyone turns a casual monocular video into multi-view videos, enabling downstream 4DGS reconstruction. Full repo under Apache 2.0💙 👉Review https://lnkd.in/p/ec4dzGvb 👉Paper https://arxiv.org/pdf/2608.20335 👉Project https://4danyone.github.io 👉Repo github.com/ant-research/4DAnyone

🔥🔥UPAL: Unified Points n' Lines🔥🔥 👉ETH (+Microsoft Spatial AI Lab) unveils a novel feature extractor that jointly extracts keypoints, lines, and feature descriptors within a single lightweight net. SOTA in line detection can be achieved by adding only three convolutional layers to existing point extractor. Repo under Apache💙 👉Review https://lnkd.in/p/eW8j5JZj 👉Paper https://arxiv.org/pdf/2608.19894 👉Repo https://github.com/francois141/upal

🐠Dual-branch Elasticity ID-Tracking🐠 👉TIDE: tracking dense, homogeneous targets, providing a scalable dual-branch design to accommodate diverse hardware constraints. MIT license💙 👉Review https://t.ly/WEDeY 👉Paper https://arxiv.org/pdf/2607.26412 👉Project https://vranlee.github.io/TIDE/ 👉Repo https://github.com/vranlee/TIDE

🔥Decoder-only Any-to-Any Model🔥 👉MODUS unifies any-to-any multimodal generation with one decoder, two experts, and zero task heads. Impressive work. Repo under Apache💙 👉Review https://t.ly/-2QKT 👉Paper https://lnkd.in/dhfBQGhB 👉Project https://lnkd.in/dPD_ECXk 👉Repo https://lnkd.in/dbDHw24u

🍿 Dawn of Generative Cinematography 🍿 🟩 #TheOdyssey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture. 👉 Meanwhile, #AI research is heading in the exact opposite direction. 🟩 A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere. 👉More https://t.ly/Kd7RV 👉Paper arxiv.org/pdf/2607.24591 👉Project yixuanli98.github.io/cameraanything/ 👉Repo github.com/yixuanli98/CameraAnything

🍿Dawn of Generative Cinematography🍿 🟩 The Odissey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture. 👉 Meanwhile, #AI research is heading in the exact opposite direction. 🟩 A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere. 🟩 Want a close-up? A drone shot? A ground-level perspective? A side angle? A cinematic tracking shot? You no longer decide where to place the camera during filming. You decide afterwards. 👉 And this fundamentally changes what cinematography means. 🟩 For more than a century, filmmakers have had to make irreversible decisions on set. Camera placement, focal length, movement, framing, etc. These choices became part of the recorded footage forever. 🟩 A scene becomes a 3D representation that can be "re-shot" endlessly from viewpoints that never physically existed. We simply capture "raw" data from which the final result is reconstructed or customized. 🟩Five years from now, will we still talk about shooting a movie? Or will we simply capture a scene and decide later where the camera should have been? The irony is fascinating. While Nolan reminds us how extraordinary a 70mm camera can be, AI is quietly suggesting that, soon, the camera itself will be optional. 👉The first step towards the generative cinematography. #deeplearning #computervision #AIwithPapers 👉Discussion https://lnkd.in/dMgakzWm 👉Paper arxiv.org/pdf/2607.24591 👉Project yixuanli98.github.io/cameraanything/ 👉Repo github.com/yixuanli98/CameraAnything

🍿🍿Dawn of Generative Cinematography🍿🍿 🟩#TheOdyssey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture. 👉Meanwhile, #AI research is heading in the exact opposite direction. 🟩A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere. 🟩Want a close-up? A drone shot? A ground-level perspective? A side angle? A cinematic tracking shot? You no longer decide where to place the camera during filming. You decide afterwards. 👉And this fundamentally changes what cinematography means. 🟩For more than a century, filmmakers have had to make irreversible decisions on set. Camera placement, focal length, movement, framing, etc. These choices became part of the recorded footage forever. 🟩A scene becomes a 3D representation that can be "re-shot" endlessly from viewpoints that never physically existed. We simply capture "raw" data from which the final result is reconstructed or customized. 🟩Five years from now, will we still talk about shooting a movie? Or will we simply capture a scene and decide later where the camera should have been? The irony is fascinating. While Nolan reminds us how extraordinary a 70mm camera can be, AI is quietly suggesting that, soon, the camera itself will be optional. 👉The first step towards the generative cinematography. #deeplearning #computervision #AIwithPapers 👉Discussion https://lnkd.in/dMgakzWm 👉Paper arxiv.org/pdf/2607.24591 👉Project yixuanli98.github.io/cameraanything/ 👉Repo github.com/yixuanli98/CameraAnything

🔎MicroZoom at Extreme Scale🔎 👉MicroZoom by UWA synthesizes gigapixel-resolution images grounded in consumer-grade microscope close-ups at magnification levels up to 350×. Impressive. Repo under MIT💙 👉Review https://t.ly/hgJD7 👉Paper https://arxiv.org/pdf/2607.24729 👉Project https://microzoom-sr.github.io/ 👉Repo github.com/MicroZoom-SR/MicroZoom-SR.github.io

💄MagicMakeup Makeup-Transfer💄 👉Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Authors: Zhejiang University & vivo BlueImage Lab. Repo for non commercial💙 👉Review https://t.ly/JYpCr 👉Paper https://arxiv.org/pdf/2607.20924 👉Project https://vivocameraresearch.github.io/magicmakeup/ 👉Repo https://github.com/vivoCameraResearch/Magic-Makeup

💢Unified Video Dense Prediction💢 👉UniD (Adobe Research + Cornell University) is a novel unified video model that jointly predicts: depth, surface normals, semantic segmentation, boundaries, human parts, albedo, shading, and materials. Code TBR💙 👉Review https://t.ly/oo7et 👉Paper https://arxiv.org/pdf/2607.21592 👉Project https://unid-video.github.io/ 👉Repo https://github.com/YihongSun/UniD

🫛Spatially-Aware Class-Agnostic Counting🫛 👉UpCount is reference-free, spatially aware, class-agnostic object counting with an MAE-pretrained ViT, DPT-style feature reassembly, FeatUp-style joint bilateral upsampling, and proposal verification. Repo under MIT💙 👉Review https://t.ly/dWOc3 👉Paper https://arxiv.org/pdf/2607.16826 👉Repo github.com/r28112072-rgb/upcount

🦜Streaming 4D Transformer🦜 👉IGGT4D is a novel a streaming instance-grounded geometry transformer for online 4D scene understanding. It processes video frames sequentially, reuses historical context through causal spatial-temporal modeling, and incrementally updates a unified representation of camera motion, geometry, and object identity. Repo/Data announced💙 👉Review https://t.ly/LFrKR 👉Paper https://arxiv.org/pdf/2607.19228 👉Project https://iggt4d.github.io/ 👉Repo TBA

👉Not a render. Not a concept. This is GENE.01 by Generative Bionics, the Italians coolest scaleup strikes back: in just six months, they turned GENE.01 into a fully functional humanoid platform that can walk, sense and interact. 👉Full-body multimodal skin perceives touch, proximity, force and temperature, bringing Physical AI closer to safe and natural collaboration with people. 👉More: https://t.ly/F3I3A

🏯SOTA Music-to-Dance Gen🏯 👉The Tongyi Lab unveils Wan-Dancer, a novel stable minute-scale synthesis at 720p/30fps across five dance genres. Impressive results, new SOTA on long clip by a large margin. Repo under Apache 2.0💙 👉Review https://t.ly/AKY5j 👉Paper https://lnkd.in/d_xA7dwb 👉Project https://lnkd.in/dzfnw2h4 👉Repo https://lnkd.in/d-Zj_cTf

🌈FlowWAM: flow->action prediction🌈 👉FlowWAM is a novel dual-stream diffusion framework that adopts optical flow as a unified, video-native action representation. Repo under Apache💙 👉Review https://t.ly/FmutT 👉Paper https://arxiv.org/abs/2607.13017 👉Project https://flow-wam.github.io/ 👉Repo github.com/YixiangChen515/FlowWAM

🦧 MonkeyOCRv2 is out! 🦧 👉MonkeyOCRv2 is a text-centric visual foundation model that unifies fine-grained text modeling, cross-task representation learning, and cross-lingual generalization in a single encoder. Released for academic research and non-commercial use💙 👉Review https://t.ly/yicEK 👉Paper https://arxiv.org/pdf/2607.11562 👉Repo https://github.com/Yuliang-Liu/MonkeyOCRv2

🎂REMIND: long-term MOT re-ID🎂 👉REMIND by CVAR-UPM is a novel online tracker designed for long-term multi-object re-ID of generic indoor objects from monocular RGB, requiring neither camera pose nor depth. Repo under MIT💙 👉Review https://t.ly/AkQoI 👉Paper https://lnkd.in/dm58mkCv 👉Project https://lnkd.in/dZrAZqFe 👉Repo https://lnkd.in/dbidrwxU

🌔Foundation Global SFM🌔 👉Glob3R is a global SfM-style reconstruction built on 3D foundation models. key idea: explicitly optimize feed-forward geometric predictions. Repo TBA💙 👉Review https://t.ly/Z_4C7 👉Paper https://arxiv.org/pdf/2607.09225 👉Project https://junyuandeng.github.io/Glob3r/ 👉Repo TBA