🦄Unified Correspondence Transformer🦄

👉UniCorrn is the first correspondence model with shared weights that unifies 2D-2D, 2D-3D, and 3D-3D geometric matching with a transformer. CC BY-NC-SA 4.0💙

👉Review https://t.ly/2OBdq
👉Paper https://arxiv.org/pdf/2605.04044
👉Project https://neu-vi.github.io/UniCorrn/
👉Repo https://github.com/neu-vi/UniCorrn

🍒Count Anything, Any Granularity🍒

👉Open-world counting as multi-grained counting, where visual exemplars specify target appearance and fine-grained text specifies the intended semantic granularity across five explicit levels. Repo/Data under Apache💙

👉Review https://t.ly/nqz80
👉Paper https://lnkd.in/dp7khTRU
👉Project https://lnkd.in/d_jfX_Yn
👉Repo https://lnkd.in/dkTRGZkG
👉Data https://lnkd.in/dB83jRyT

🪔Latent Decoding Pixel Diffusion🪔

👉PiD by Nvidia is a plug-and-play diffusion decoder that replaces VAE/RAE decoders, turning latent representations directly into super-resolved pixels in a single pass. Repo under Apache 2.0💙

👉Review https://t.ly/y19mA
👉Paper https://lnkd.in/duVC25C2
👉Project https://lnkd.in/dW6TkzCB
👉Repo https://lnkd.in/dnGdgKRr

🔍 Nvidia Locate Anything 🔍

👉Diverse localization tasks under a unified vision-language model, including document understanding, GUI grounding, dense detection, and OCR. Repo released💙

👉Review https://t.ly/PvwFo
👉Paper https://lnkd.in/dWfNpzPZ
👉Project https://lnkd.in/dM89BX-8
👉Repo https://lnkd.in/dC4KCQSM

🕷️Human Universal Grasping🕷️

👉HUG is a flow-matching model that generates diverse human grasps for any user-specified object in a single RGB-D image captured from a stereo camera.

👉Review https://t.ly/VG1Eu
👉Paper https://arxiv.org/pdf/2606.17054
👉Repo https://github.com/KevinyWu/hug
👉Project https://grasping.io/

🔊VolHuMe - Volumetric Human Meshes🔊

👉VolHuMe (H/T @Martinella_94) is a novel, high-resolution large-scale dataset of volumetric human meshes with complete 4D GT: multi-view RGB-D, textured meshes, dense point clouds, normal maps, rigged assets, garment segmentation, and SMPL-X fittings in one dataset. Insane💙

👉Review https://t.ly/b5vxy
👉Paper https://arxiv.org/pdf/2606.23062
👉Project giuli13.github.io/volhume-website/#
👉Repo TBA soon

👋 Hi everyone!

Over the past few weeks, the number of join requests has increased dramatically, which unfortunately also means a much higher number of spam and bots (in the last days around five hundreds been cut off)

To help me distinguish real people from fake profiles - and avoid rejecting genuine requests by mistake - I'd really appreciate if your profile includes:
📷 A real profile photo
👤 Your full name (or something reasonably identifiable)
💬 If you contact me, please use English if possible.

I don't speak Russian, Arabic, or Chinese, so if your profile and messages are only in those languages, it's very difficult for me to tell whether you're a real person or an automated account. Thank you for your understanding and for helping keep this damn community welcoming and spam-free!

With love,
Alessandro 😈

🍀OctoSense: Open Sensing🍀

👉OctoSense is an open-source sensor platform with stereo RGB and event cameras, LiDAR, a thermal camera, an inertial measurement unit, RTK-corrected global positioning system, and proprioception.

👉Review https://t.ly/oFN8L
👉Paper https://lnkd.in/dM3zpyju
👉Project https://lnkd.in/ddrQ3uJ6
👉Repo https://lnkd.in/dhSDjSfG

🛸PriorEye: Geospatial Self-Driving🛸

👉MRG (Oxford) introduces geospatial visual priors to leverage the street-level images in autonomous driving. Consistent improvement in performance. Repo under Apache💙

👉Review https://t.ly/7Jgav
👉Paper https://lnkd.in/dYeD2m7n
👉Project https://lnkd.in/dWJvNemr
👉Repo https://lnkd.in/dNExGGtx

🌒LUNA: Universal 3D Animation🌔

👉LUNA by HKUST + META is a novel LBS-free universal neural animation model that directly maps multiple 2D controls like images, keypoints, sketch and unseen characters into 3D-G deformations, bypassing explicit body fitting.

👉Review https://t.ly/ZX9Ex
👉Paper https://arxiv.org/pdf/2606.31981
👉Project https://penghtyx.github.io/LUNA/
👉Repo N/A 🥲

🔥Nvidia SpatialClaw is out🔥

👉From Nvidia a novel training-free framework for spatial reasoning that adopts code as the action interface. SpatialClaw lets a VLM-backed agent write Python in a persistent kernel, composing perception modules, inspecting intermediate results, and revising its strategy across steps. Impressive: +11.2 points on 20 benchmarks💙

👉Review https://t.ly/7JB0x
👉Paper https://arxiv.org/pdf/2606.13673
👉Project https://spatialclaw.github.io/
👉Repo https://github.com/NVlabs/SpatialClaw

🏯Worldwide Semantic Facade🏯

👉A centimeter-accurate / cross-continental facade point clouds, with fine-grained semantic segmentation of architectural elements, and hierarchical facade taxonomy. 2.7B Dataset💙

👉Review https://t.ly/PpyFD
👉Paper https://arxiv.org/pdf/2607.02018
👉Project jiangyuanwangyi.github.io/UnderOneFacade_official
👉Data drive.google.com/drive/folders/1Yzz7PmyeK1qeOtkTFCfkbw7IEHXcMJo8

🐈‍⬛Spatial-perception native ViT🐈‍⬛

👉LingBot-Vision, a vision foundation model pretrained to be spatial-perception native. Better than 7x bigger foundational models. Repo under Apache💙

👉Review https://t.ly/9xIso
👉Paper https://arxiv.org/pdf/2607.05247
👉Project https://technology.robbyant.com/lingbot-vision
👉Repo https://github.com/robbyant/lingbot-vision

🏵️SoccerNet 2026 Results🏵️

👉The SoccerNet 2026 Challenges constitute the sixth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in sports video understanding💙

👉Review https://t.ly/sfD4T
👉Paper https://lnkd.in/dSBgW_3s
👉Project https://lnkd.in/dfdmuvG8

🔥ZipDepth: Depth on Any Device🔥

👉ZipDepth from UniBO is a super-compact monocular depth network by combining an efficient reparameterizable encoder-decoder with large-scale knowledge distillation from a foundation model. Repo under MIT💙

👉Review https://t.ly/qYrLZ
👉Paper https://arxiv.org/pdf/2607.08771
👉Project https://zipdepth.github.io/
👉Repo https://github.com/fabiotosi92/ZipDepth

💋SAM-MT: Real-Time Multi-Target VOS💋

👉Fudan & Shangai unveil SAM-MT, an efficient interactive multi-target video segmentation framework that maintains near-single-object efficiency (FPS/VRAM) as target count increases, while maintaining robust video segmentation performance. Repo available💙

👉Review https://t.ly/Z_4C7
👉Paper https://lnkd.in/dvS-iyBD
👉Project https://lnkd.in/daQ8na8T
👉Repo https://lnkd.in/dgbX2tZv

🌔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

🎂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

🦧 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