🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Ever noticed how one scene seamlessly transitions into another in films? That’s a match-cut—a subtle yet powerful cinematic trick. Our MatchDiffusion, generates two videos from text prompts, designed to form a seamless match-cut—effortlessly and training-free. 🎥✨ 1/n

(1/) I'll be going to #NeurIPS2024 next week, where I'll be presenting exciting new work on detecting gaming using causal inference! Our work is motivated by some problems in Medicare (U.S. public health insurance): turns out it's incredibly easy to game that system.

🚀 Introducing CausVid: Instant video generation that plays the moment you hit "Generate", while maintaining state-of-the-art quality! Project Page: causvid.github.io. More details in the long thread.

🌍 Guessing where an image was taken is a hard, and often ambiguous problem. Introducing diffusion-based geolocation—we predict global locations by refining random guesses into trajectories across the Earth's surface! 🗺️ Paper, code, and demo: nicolas-dufour.github.io/plonk

I'll be presenting "Images that Sound" today at #NeurIPS2024! East Exhibit Hall A-C #2710. Come say hi to me and Andrew Owens :) (Ziyang Chen sadly could not make it, but will be there in spirit :') )

I had a lot of fun helping put this problem set together -- if you're teaching diffusion models + computer vision, consider using this homework for your course! (links at end of Ryan Tabrizi's thread!)

Hey all, I'll be answering questions about our "Motion Prompting" paper on alphaXiv (alphaXiv) (it's like arXiv, but adds a discussion section, and I think is quite well built!): alphaxiv.org/abs/2412.02700…

Decentralized Diffusion Models power stronger models trained on more accessible infrastructure. DDMs mitigate the networking bottleneck that locks training into expensive and power-hungry centralized clusters. They scale gracefully to billions of parameters and generate

Our workshop at #ICLR2025 is now open to submissions until 02/03 🥳 check our website if you are interested: sites.google.com/view/icbinb-20…

A sister team to ours at Google DeepMind is looking for student researchers this summer. Please reach out if you are a PhD student working on media generation (diffusion models), or if you are a professor with students to recommend! 😀

Ever wish YouTube had 3D labels? 🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose! Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯 Download: huggingface.co/datasets/nvidi…

Really cool paper about training interactivity into a video model with surprisingly little data! Great work!

Can AI image detectors keep up with new fakes? Mostly, no. Existing detectors are trained using a handful of models. But there are thousands in the wild! Our work, Community Forensics, uses 4800+ generators to train detectors that generalize to new fakes. #CVPR2025 🧵 (1/5)

Ever wondered how a scene sounds👂 when you interact👋 with it? Introducing our #CVPR2025 work "Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes" -- we make 3D scene reconstructions audibly interactive! yimingdou.com/hearing_hands/

Excited to share our CVPR 2025 paper on cross-modal space-time correspondence! We present a method to match pixels across different modalities (RGB-Depth, RGB-Thermal, Photo-Sketch, and cross-style images) — trained entirely using unpaired data and self-supervision. Our