Shariq Farooq (@shariq_farooq) 's Twitter Profile
Shariq Farooq

@shariq_farooq

PhD @ KAUST👨‍💻 | Worked with @intel , @Adobe , @Stanford @ucl | Author of ZoeDepth, AdaBins, LooseControl | Exploring the 3D world, one image at a time 🔍 |

ID: 586833294

linkhttp://shariqfarooq123.github.io calendar_today21-05-2012 18:18:50

227 Tweet

340 Followers

495 Following

Shariq Farooq (@shariq_farooq) 's Twitter Profile Photo

PatchFusion, our new 4K depth estimation model, significantly improves the details and quality of depth maps produced by ZoeDepth 👇

Alex Carlier (@alexcarliera) 's Twitter Profile Photo

LooseControl was just released and it's so good! 🔥 It enables depth-map conditioned image generation, but unlike ControlNet, the 3D boxes enable less strict control with simple bounding boxes. And look at how stable it is across frames! More examples (with code) below ⬇️⬇️

Alex Carlier (@alexcarliera) 's Twitter Profile Photo

PatchFusion was just released. Compared to ZoeDepth, it predicts depth maps with much finer details, just look at the comparison below! 🤯 Its main contribution is a new Global-to-Local module and Consistency-Aware Training. More examples below (with code) ⬇️⬇️

80 LEVEL (@80level) 's Twitter Profile Photo

Researchers presented LooseControl, a model that can change AI-generated images by using 3D boxes. You can set up the boxes, and the tool will generate an image based on their positions and sizes. Try the demo: 80.lv/articles/turni… #AI #GenerativeAI #controlnet #technews

AK (@_akhaliq) 's Twitter Profile Photo

PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation Gradio demo is out on Hugging Face demo: huggingface.co/spaces/zhyever… run with docker: huggingface.co/spaces/zhyever… duplicate space with private gpu and no queue:

Gradio (@gradio) 's Twitter Profile Photo

Two excellent Depth estimation models have recently come out- 1⃣PatchDiffusion (Zhenyu Li,Shariq Farooq et al.) 2⃣Marigold from ETH Zürich team (KeBingxin, Anton Obukhov et al.) Code and examples in tweets below

Two excellent Depth estimation models have recently come out-
1⃣PatchDiffusion (<a href="/zhenyu_li9955/">Zhenyu Li</a>,<a href="/shariq_farooq/">Shariq Farooq</a> et al.)
2⃣Marigold from ETH Zürich team (<a href="/KBingxin/">KeBingxin</a>, <a href="/AntonObukhov1/">Anton Obukhov</a> et al.)

Code and examples in tweets below
Shariq Farooq (@shariq_farooq) 's Twitter Profile Photo

PatchFusion lifts ZoeDepth to very high resolution and natively supports 4K+ input! Can’t wait to see the community trying it out for various applications where ZoeDepth couldn’t provide the details!

Abdelrahman Eldesokey (@abdo_eldesokey) 's Twitter Profile Photo

Check out my most recent work with Peter Wonka : "Text2AC-Zero" for generating videos of Animated Characters using pre-trained 2D diffusion models. Our approach is temporally consistent, zero-shot and requires only text prompt as input. Project page: abdo-eldesokey.github.io/text2ac-zero/

Ivan Skorokhodov (@isskoro) 's Twitter Profile Photo

This paper has received significantly less attention than it deserves, so let me shed a bit more light on it and describe why it's so good: 1. It turns out that the classical U-Net image diffusion backbone, which the entire community has been happily building upon during the

Matt Menendez (@mezdez) 's Twitter Profile Photo

Testing Image to #3D in ZoeDepth and exporting out to Blender - still need to figure out how to map the image back Thanks Shariq Farooq ! 🤘

OpenAI (@openai) 's Twitter Profile Photo

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

Eduardo Borges (@duborges) 's Twitter Profile Photo

This video was generated by Sora. That's the new model by OpenAI. The most advanced text-to-video tool created so far. I'll share the videos here. Absolutely insane. Prompt: This close-up shot of a Victoria crowned pigeon showcases its striking blue plumage and red chest. Its

Jürgen Schmidhuber (@schmidhuberai) 's Twitter Profile Photo

I am hiring 3 postdocs at #KAUST to develop an Artificial Scientist for discovering novel chemical materials for carbon capture. Join this project with Francesco Faccio @ ICLR2025 🇸🇬 at the intersection of RL and Material Science. Learn more and apply: faccio.ai/postdoctoral-p…

I am hiring 3 postdocs at #KAUST to develop an Artificial Scientist for discovering novel chemical materials for carbon capture. Join this project with  <a href="/FaccioAI/">Francesco Faccio @ ICLR2025 🇸🇬</a> at the intersection of RL and Material Science. Learn more and apply: faccio.ai/postdoctoral-p…
Rameen Abdal (@abdalrameen) 's Twitter Profile Photo

What if you could compose videos— merging multiple clips, even capturing complex athletic moves where video models struggle - all while preserving motion and context? And yes, you can still edit them with text after! Stay tuned for more results. #AI #VideoGeneration #SnapResearch