🧁🧁The new SOTA in RVOS (semantic segmentation + captions) just open-sourced🧁🧁

👉RVOS task involves segmentation of a text-referred object instance in the… | 22 comments on LinkedIn

🥝🥝HyperStyle, a hypernetwork to modulate StyleGAN for Hi-Fi inversion, just open-sourced🥝🥝

👉Inversion of real images into StyleGAN’s latent space is an…

👽👽SAFA, a novel structure-aware neural generator, just open-sourced👽👽

👉GAN has made great progress on the face animation task. However, without knowing...

🔴🟢 Berkeley unveils PHALP, a novel 3D tracking by appearance, location & pose 🔴🟢

👉Novel approach for tracking people in monocular videos by predicting… | 10 comments on LinkedIn

🚶‍♂️🚶🚶‍♀️ Do pedestrians pay attention? 🚶‍♂️🚶🚶‍♀️

👉 Humans rely on eye contact for fast/efficient communication with nearby people. Autonomous...

🍉🍉 Plenoxel: Radiance Fields 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 neural networks 🍉🍉

👉Berkeley unveils Plenoxel, a view-dependent sparse voxel model that can optimize ...

🍠🍠 ViT Deep features for Co-segmentation, Part Co-segmentation, and Semantic Correspondences 🍠🍠

👉“Deep Features” extracted from the activation of layers…

🥭🥭Real-ESRGAN: Super-Resolution with pure Synthetic Data🥭🥭

👉Single image super-resolution topic aims at reconstructing a high-resolution image from its… | 16 comments on LinkedIn

😮The Chinese #Musk doppelganger: #deepfake or… | 11 comments on LinkedIn

🤩🤩The SOTA in video instance segmentation is insane (every day better)🤩🤩

👉SeqFormer is the frustratingly simple model for video instance segmentation…

✂️🧴The #AI Barbershop source code is out! 🧴✂️

👉Even though recent work on GANs enables synthesis of realistic hair or faces, it remains difficult to… | 20 comments on LinkedIn

🐸🐸 StyleGAN-V: new SOTA in Continuous Video Generation is magic 🐸🐸

👉StyleGAN-V extends the recent paradigm of neural representations to the video generation domain. KAUST & #Snap show with this model that is possible to generate arbitrarily long clips at…

🤹‍♀️🤹‍♂️“Splice" #AI: painting the structure of an image with the appearance of another one🤹‍♀️🤹‍♂️

👉WAIC unveils an #AI to generate objects in a source structure image “painted” with the visual appearance of their semantically related objects in a target…

😮🤩 WebToonMe project made my day 😮🤩

- Webtoon Me: https://lnkd.in/dSi2JjvS
- Webtoon Painter: https://lnkd.in/d-2_Y3Bp
- Company: https://lnkd.in/dcVbemiz

#artificialintelligence #machinelearning #deeplearningai #deepneuralnetworks #neuralnetworks #ml …

😵‍💫🤪SeamlessGAN, endless texture generator, is hypnotic😵‍💫🤪

👉Real-time graphics requires HQ textured materials to convey realism in virtual env. Generating textures is challenging as they need to be realistic, seamlessly tileable, and low-memory.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:…

🦚🦚ELSED: the best/fastest line detector ever🦚🦚

👉Detecting local features, such as corners, segments or blobs, is the first step in the pipeline of many #computervision applications. Its speed is crucial for real-time applications.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅ELSED: Enhanced…

🦎🦎GANmouflage: learn to non-detecting objects🦎🦎

👉GANmouflage by UMich & Berkeley learns to camouflage 3D objects within scenes. Given an object’s... 23 comments on LinkedIn

👕👚Re-rendering human fashion style with GAN👚👕

👉VT + Adobe are open sourcing a new algorithm for generating detail-preserving and photo-realistic… | 19 comments on LinkedIn