Trending papers today

Top 5 trending papers today from my twitter feed

1. Track Anything: Segment Anything Meets Videos

   abs: https://arxiv.org/abs/2304.11968

   github: https://github.com/gaomingqi/Track-Anything

   

2. HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

   abs: https://arxiv.org/abs/2304.12281

   project page: https://showlab.github.io/HOSNeRF/

3. Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations

   abs: https://arxiv.org/abs/2304.11267

4. AutoNeRF: Training Implicit Scene Representations with Autonomous Agents abs: https://arxiv.org/abs/2304.11241

   project page: https://pierremarza.github.io/projects/autonerf/

5. Segment Anything in 3D with NeRFs

   abs: https://arxiv.org/abs/2304.12308

   project page: https://jumpat.github.io/SA3D/

Bonus:

HuggingChat

Powered by Open Assistant's latest model – the best open source chat model right now and the Hugging Face Inference API. Try it out now: http://hf.co/chat