Ziwei Liu (@liuziwei7) / X

Ziwei Liu

2,283 posts

Ziwei Liu

@liuziwei7

Associate Professor @NTUsg - Vision, Learning and Embodied AI | Building @ropedia_ai

Singapore

Joined January 2018

Ziwei Liu
@liuziwei7
Dec 1, 2023
🔥🔥We are excited to announce #Vchitect, an open-source project for video generative models @huggingface 📽️LaVie (Text2Video Model) - Code: github.com/Vchitect/LaVie - huggingface.co/spaces/Vchitec… 📽️SEINE (Image2Video Model) - Code: github.com/Vchitect/SEINE - huggingface.co/spaces/Vchitec…
00:00
357K
Ziwei Liu
@liuziwei7
Apr 27, 2023
We are presenting **SAD** (Segment Any RGBD): SAD is able to perform 3D segmentation (segment out any 3D object) with RGBD inputs (or rendered depth images only). - Code: github.com/Jun-CEN/Segmen… - Demo @huggingface: huggingface.co/spaces/jcenaa/…
00:00
196K
Ziwei Liu
@liuziwei7
Oct 2, 2023
🔥MoCap Anybody🔥 #NeurIPS2023 We propose *SMPLer-X*, the first generalist foundation model for 3D/4D human motion capture from monocular inputs. - Project: caizhongang.github.io/projects/SMPLe… - Paper: arxiv.org/abs/2309.17448 - Code: github.com/caizhongang/SM… - Demo: youtube.com/watch?v=DepTqb…
00:00
186K
Ziwei Liu
@liuziwei7
Apr 24, 2023
Check out **RAM** (Relate Anything Model) ! - We empower Segment Anything Model (SAM) with the capability to recognize various visual relations between different visual concepts. - Code: github.com/Luodian/Relate… - Demo @huggingface: huggingface.co/spaces/mmlab-n…
00:00
126K
Ziwei Liu
@liuziwei7
Apr 30, 2023
Thrilled to announce **Otter**, a multi-modal in-context learning model with instruction tuning: 1) Chatbot w/ image, video, 3D 2) Only need 4x 3090 GPUs 3) Better than OpenFlamingo - Code: github.com/Luodian/otter - Demo: otter.cliangyu.com - Video: youtube.com/watch?v=r-YM4D…
67K
Ziwei Liu
@liuziwei7
Feb 19, 2024
🔥Open-Source Video Diffusion Transformer🔥 Similar to #Sora, our ☕️Latte☕️ model also has *video diffusion transformer* architecture, with thorough study on the design space of *LDM + DiT* for video generation - Project: maxin-cn.github.io/latte_project/ - Code: github.com/Vchitect/Latte
OpenAI
@OpenAI
Feb 15, 2024
Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. openai.com/sora Prompt: “Beautiful, snowy
00:00
65K
Ziwei Liu
@liuziwei7
Jun 16, 2020
We are releasing, #OpenSelfSup, an open-source library for self-supervised learning: github.com/open-mmlab/Ope… - *All methods in one repository*, supporting PIRL, MoCo, SimCLR, etc. - *All benchmarks in one repository*. - *Efficiency*, supporting multi-GPU distributed training.
Ziwei Liu
@liuziwei7
Apr 22, 2023
Our F2-NeRF is open sourced at: github.com/totoro97/f2-ne… . Feel free to create your own free-trajectory NeRF within 10min :)
AK
@_akhaliq
Mar 29, 2023
F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories abs: arxiv.org/abs/2303.15951 project page: totoro97.github.io/projects/f2-ne…
00:00
GitHub - Totoro97/f2-nerf: Fast neural radiance field training with free camera trajectories
From github.com
77K
Ziwei Liu
@liuziwei7
Feb 4, 2024
🔥Generative Gaussian Splatting🔥 #ICLR2024 Our 🚀DreamGaussian🚀 is accepted to @iclr_conf as **oral presentation**, enabling high-quality 3D generation in 2 minutes - Project: dreamgaussian.github.io - Code: github.com/dreamgaussian/… - Demo @huggingface: huggingface.co/spaces/jiawei0…
00:00
00:28
AK
@_akhaliq
Sep 29, 2023
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation paper page: huggingface.co/papers/2309.16… Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been
52K
Ziwei Liu
@liuziwei7
Jul 3, 2022
We have released, DeepFashion-MultiModal, a large-scale high-quality human dataset with rich multi-modal annotations: github.com/yumingj/DeepFa… - 40K high-resolution human images - Human parsing, keypoints and DensePose annotations - Attribute and textual description annotations
02:06
AK
@_akhaliq
Jun 1, 2022
Text2Human: Text-Driven Controllable Human Image Generation abs: arxiv.org/abs/2205.15996 project page: yumingj.github.io/projects/Text2… github: github.com/yumingj/Text2H…
Ziwei Liu
@liuziwei7
Sep 29, 2023
🔥🔥 We propose #DreamGaussian, a Generative Gaussian Splatting framework that produces high-quality textured meshes in just 2 minutes from a single-view image. - Project: dreamgaussian.github.io - Paper: arxiv.org/abs/2309.16653 - Code: github.com/dreamgaussian/…
00:00
00:28
AK
@_akhaliq
Sep 29, 2023
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation paper page: huggingface.co/papers/2309.16… Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been
82K
Ziwei Liu
@liuziwei7
Jan 23, 2024
🔥Text-to-3D Foundation Model🔥 We are excited to announce #3DTopia, a generalist 🧊text-to-3D🧊 foundation model, which produces ** high-quality 3D assets within 5 minutes ** - Code: github.com/3DTopia/3DTopia - Video: youtube.com/watch?v=yybCrf…
00:00
63K
Ziwei Liu
@liuziwei7
May 8, 2023
Now you can create 3D fantasy world by combining #SceneDreamer with #ControlNet :) - Code: github.com/FrozenBurning/… - Demo @huggingface: huggingface.co/spaces/FrozenB…
00:00
00:58
AK
@_akhaliq
Feb 3, 2023
SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections abs: arxiv.org/abs/2302.01330 project page: scene-dreamer.github.io
113K
Ziwei Liu
@liuziwei7
Mar 3, 2024
📢Motion Capture from Any Video📢 The @Gradio demo for 🚀SMPLer-X🚀 (foundation model for monocular 3D human motion capture) is now online thanks to @_akhaliq! - Project: caizhongang.com/projects/SMPLe… - Code: github.com/caizhongang/SM… - Online Demo @huggingface: huggingface.co/spaces/caizhon…
Ziwei Liu
@liuziwei7
Oct 2, 2023
🔥MoCap Anybody🔥 #NeurIPS2023 We propose *SMPLer-X*, the first generalist foundation model for 3D/4D human motion capture from monocular inputs. - Project: caizhongang.github.io/projects/SMPLe… - Paper: arxiv.org/abs/2309.17448 - Code: github.com/caizhongang/SM… - Demo: youtube.com/watch?v=DepTqb…
00:00
70K