🆔🆔 Magic-Me: Identity-Specific Video 🆔🆔

👉hashtag#ByteDance (+UC Berkeley) unveils VCD for video-gen: with just a few images of a specific identity it can generate temporal consistent videos aligned with the given prompt. Impressive results, source code under Apache 2.0 💙

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Novel Video Custom Diffusion (VCD) framework
✅High-Quality ID-specific videos generation
✅Improvement in aligning IDs-images and text
✅Robust 3D Gaussian Noise Prior for denoising
✅Better Inter-frame correlation / video consistency
✅New modules F-VCD/T-VCD for videos upscale
✅New train with masked loss by prompt-to-segmentation

hashtag#artificialintelligence hashtag#machinelearning hashtag#ml hashtag#AI hashtag#deeplearning hashtag#computervision hashtag#AIwithPapers hashtag#metaverse

👉Channel: @deeplearning_ai
👉Paper https://arxiv.org/pdf/2402.09368.pdf
👉Project https://magic-me-webpage.github.io/
👉Code https://github.com/Zhen-Dong/Magic-Me

Introducing ECoDepth: The New Benchmark in Diffusive Mono-Depth

From the labs of IITD, we unveil ECoDepth - our groundbreaking SIDE model powered by a diffusion backbone and enriched with ViT embeddings. This innovation sets a new standard in single image depth estimation (SIDE), offering unprecedented accuracy and semantic understanding.

Key Features:

✅Revolutionary MDE approach tailored for SIDE tasks
✅Enhanced semantic context via ViT embeddings
✅Superior performance in zero-shot transfer tasks
✅Surpasses previous SOTA models by up to 14%

Dive into the future of depth estimation with ECoDepth. Access our source code and explore the full potential of our model.

📖 Read the Paper
💻 Get the Code

#ArtificialIntelligence #MachineLearning #DeepLearning #ComputerVision #AIwithPapers #Metaverse

join our community:
👉 @deeplearning_ai