Sublime

📢Hot off the presses: we present **DiffusionNet** for simple and scalable deep learning on surfaces. The networks generalize by construction across different samplings, resolutions, and even representations. Spatial support is automatically optimized as a parameter! 🧵👇 (1/N) https://t.co/E2CRp37cuG

eDiffi: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers abs: https://t.co/QaJfNzXeLL project page: https://t.co/UrYmzGek8C sota t2i diffusion model that consists of a base diffusion model and two super-resolution modules, 1024 × 1024 high-definition outputs... See more

Excited to present DINO-Tracker (accepted to #ECCV2024)! A novel self-supervised method for long-range dense tracking in video, which harnesses the powerful visual prior of DINO. Project page: https://t.co/01sos2w624. [1/4] @assaf_singer... See more

🔥DELTA: Dense Efficient Long-range 3D Tracking for any video DELTA can efficiently (10x faster!) track EVERY pixel in 3D space from monocular videos. Please check out our project page and paper for more details and samples! 👑https://t.co/nVQeP5LNLO https://t.co/hGBfIq7RLJ

@BamChrisAI OpenShape from my lab might be particularly useful here. strong embeddings designed for 3D searchable by text, images or pointcloud: https://t.co/BzIE5uB3S5