Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Happy to share our new work, MVInverse, a feedforward framework for multiview PBR material estimation at ~10 fps. Multiview ViT (like VGGT, Pi3) can also do material estimation! Paper: Homepage: Code:

Yuan Liu

1,982 subscribers

11,933 views • 8 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Excited to share our recent work, UniSH, which unifies dynamic 3D scene reconstruction and SMPL estimation within a single framework. (Left-top is input video). Code has been released! Project page: Paper:

Excited to share our recent work, UniSH, which unifies dynamic 3D scene reconstruction and SMPL estimation within a single framework. (Left-top is input video). Code has been released! Project page: Paper:

Yuan Liu

19,258 views • 8 months ago

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

(1/10) 🔥Thrilled to introduce OneDiffusion—our latest work in unified diffusion modeling! 🚀 This model bridges the gap between image synthesis and understanding, excelling in a wide range of tasks: T2I, conditional generation, image understanding, identity preservation, multiview generation, and even camera pose estimation. Learn more at: Project: arXiv: Code (on the way):

Jiasen Lu

33,426 views • 1 year ago

Excited to share our #CHI2026 paper “Texterial: A Text-as-Material Interaction Paradigm for LLM-Mediated Writing” (done during internship at Microsoft Research) We imagine interacting with LLMs by treating text as a material like plants/clay. 📃 🧵[1/n]

Excited to share our #CHI2026 paper “Texterial: A Text-as-Material Interaction Paradigm for LLM-Mediated Writing” (done during internship at Microsoft Research) We imagine interacting with LLMs by treating text as a material like plants/clay. 📃 🧵[1/n]

Jocelyn Shen

19,855 views • 6 months ago

Because this was a non-union PSA, I can share it again without violating the strike. At a time when we are starved for new material, it is comforting to know that we still have access to content like this. Please watch and share. #TBT

Because this was a non-union PSA, I can share it again without violating the strike. At a time when we are starved for new material, it is comforting to know that we still have access to content like this. Please watch and share. #TBT

Misha Collins

169,129 views • 3 years ago

We release a new urban simulator, MetaUrban, to support research on AI agents for micromobility. The work will be presented at #ICLR2025, and the demo code can run on any laptop. Webpage: Code: Paper:

We release a new urban simulator, MetaUrban, to support research on AI agents for micromobility. The work will be presented at #ICLR2025, and the demo code can run on any laptop. Webpage: Code: Paper:

Bolei Zhou

30,344 views • 1 year ago

Excited to share our new work: StreamingVLM! 🚀 We tackle a major challenge for Vision-Language Models (VLMs): understanding infinite video streams in real-time without latency blowing up or running out of memory. Paper: Code:

Excited to share our new work: StreamingVLM! 🚀 We tackle a major challenge for Vision-Language Models (VLMs): understanding infinite video streams in real-time without latency blowing up or running out of memory. Paper: Code:

Guangxuan Xiao

92,141 views • 11 months ago

Check out our new Material Separation Photoshop Plug-in! Live2D Cubism 5 Material Separation Photoshop Plugin R1 alpha now available! The Material Separation Photoshop Plug-in is a Photoshop plug-in that makes it easy to perform material separation, the preliminary step in Live2D modeling. The cutting out, color filling and transparency filling of the material are performed semi-automatically. (Adobe® Photoshop®software) ▼Download it here: ▼How to use the Plug-in: *A Cubism PRO license is required for use. *The plug-in can also be used during the 42-day Live2D Cubism PRO free trial. #Live2D

Check out our new Material Separation Photoshop Plug-in! Live2D Cubism 5 Material Separation Photoshop Plugin R1 alpha now available! The Material Separation Photoshop Plug-in is a Photoshop plug-in that makes it easy to perform material separation, the preliminary step in Live2D modeling. The cutting out, color filling and transparency filling of the material are performed semi-automatically. (Adobe® Photoshop®software) ▼Download it here: ▼How to use the Plug-in: A Cubism PRO license is required for use. The plug-in can also be used during the 42-day Live2D Cubism PRO free trial. #Live2D

Live2D

62,871 views • 2 years ago

We are thrilled to share our breakthrough research on "Agile Flight from Pixels without State Estimation," to be presented and live-demonstrated at #RSS2024 next week! You heard well: no state estimation means no explicit visual localization, no SLAM, no VIO, and no IMU! Paper: Video (Narrated): Last year, we demonstrated that #ReinforcementLearning (RL) policies could outperform world-champion drone-racing pilots using the same quadrotor hardware; however, unlike human pilots, these policies continuously estimated an explicit state from known gate positions, the camera feed, and inertial measurements (IMU). In this new work, we tackle the challenge of learning vision-based drone racing using an end-to-end reinforcement learning approach that eliminates the need for IMU data or explicit state estimation. Like professional pilots, we go directly from images to control commands. The training is facilitated by an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use an appropriate sensor representation, which can be efficiently simulated during training without rendering images. We achieve agile flight at speeds up to 40 km/h with accelerations up to 2 g's. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments. Besides the paper presentation, we will also give a live demo next Tuesday and Wednesday between and hrs at TU Delft: Reference: Ismail Geles*, Leonard Bauersfeld*, Angel Romero, Jiaxu Xing, Davide Scaramuzza "Demonstrating Agile Flight from Pixels without State Estimation" Robotics: Science and Systems (RSS), 2024. Kudos to Ismail Geles Leonard Bauersfeld Ángel Romero Jiaxu Xing! University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)

We are thrilled to share our breakthrough research on "Agile Flight from Pixels without State Estimation," to be presented and live-demonstrated at #RSS2024 next week! You heard well: no state estimation means no explicit visual localization, no SLAM, no VIO, and no IMU! Paper: Video (Narrated): Last year, we demonstrated that #ReinforcementLearning (RL) policies could outperform world-champion drone-racing pilots using the same quadrotor hardware; however, unlike human pilots, these policies continuously estimated an explicit state from known gate positions, the camera feed, and inertial measurements (IMU). In this new work, we tackle the challenge of learning vision-based drone racing using an end-to-end reinforcement learning approach that eliminates the need for IMU data or explicit state estimation. Like professional pilots, we go directly from images to control commands. The training is facilitated by an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use an appropriate sensor representation, which can be efficiently simulated during training without rendering images. We achieve agile flight at speeds up to 40 km/h with accelerations up to 2 g's. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments. Besides the paper presentation, we will also give a live demo next Tuesday and Wednesday between and hrs at TU Delft: Reference: Ismail Geles, Leonard Bauersfeld, Angel Romero, Jiaxu Xing, Davide Scaramuzza "Demonstrating Agile Flight from Pixels without State Estimation" Robotics: Science and Systems (RSS), 2024. Kudos to Ismail Geles Leonard Bauersfeld Ángel Romero Jiaxu Xing! University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)

Davide Scaramuzza

27,959 views • 2 years ago

Notion's Head of Product Max Schoening : "I actually don't care at all whether designers write code that lands in production. The reason I like designers thinking in code is that it forces you to consider the medium. I would much rather take a designer or PM who has a deep affinity for understanding how agent loops work than someone who can ship PRs. And the only way that you can actually get to understanding agent loops is by building them in the material that they're made of, which is currently code. That's why I care that designers 'code.' Not because of the utility of shipping to production, but because it forces you to really interrogate the material that you're designing with."

Notion's Head of Product Max Schoening : "I actually don't care at all whether designers write code that lands in production. The reason I like designers thinking in code is that it forces you to consider the medium. I would much rather take a designer or PM who has a deep affinity for understanding how agent loops work than someone who can ship PRs. And the only way that you can actually get to understanding agent loops is by building them in the material that they're made of, which is currently code. That's why I care that designers 'code.' Not because of the utility of shipping to production, but because it forces you to really interrogate the material that you're designing with."

Lenny Rachitsky

76,527 views • 4 months ago

A NEW ERA FOR BEGINS TODAY! We are excited to announce the launch of our new $WIK-ED UI and couldn’t be more happy to share it with you all! Everything is now cleaner and accessible within just one click. From a completely new homepage to new sportsbook everything has been upgraded. You can even flex with your rank in live bets 😉 Here’s to the future of and $WIK. Don’t forget to stay tuned for our biggest ad campaign yet! 🫡

A NEW ERA FOR BEGINS TODAY! We are excited to announce the launch of our new $WIK-ED UI and couldn’t be more happy to share it with you all! Everything is now cleaner and accessible within just one click. From a completely new homepage to new sportsbook everything has been upgraded. You can even flex with your rank in live bets 😉 Here’s to the future of and $WIK. Don’t forget to stay tuned for our biggest ad campaign yet! 🫡

WickedBet.com

49,102 views • 1 year ago

JUST IN: Ukrainian President Volodymyr Zelenskyy thanks President Trump for bipartisan American support in their war against Russia at the high-stakes NATO summit, stressing that cutting a new "drone deal" and securing advanced air defense remain Ukraine's absolute top priorities. "We're thankful as always to your support. American support, bipartisan support. thanks for an invitation to this summit.” “Air defense is the priority. The second point, or maybe the first. And, about negotiations, I think, yes, we understand what to do is our estimation, what to do, how to bring this. And I hope that we will do. I'm sure that you will do everything to solve this war. Yeah. And I'm very happy that our side began to work on, drone deal."

JUST IN: Ukrainian President Volodymyr Zelenskyy thanks President Trump for bipartisan American support in their war against Russia at the high-stakes NATO summit, stressing that cutting a new "drone deal" and securing advanced air defense remain Ukraine's absolute top priorities. "We're thankful as always to your support. American support, bipartisan support. thanks for an invitation to this summit.” “Air defense is the priority. The second point, or maybe the first. And, about negotiations, I think, yes, we understand what to do is our estimation, what to do, how to bring this. And I hope that we will do. I'm sure that you will do everything to solve this war. Yeah. And I'm very happy that our side began to work on, drone deal."

Fox News

109,768 views • 2 months ago

Do you also feel this desire for hot latex, the material, the shine, the dominance? I don't want to give too much information but take a look at my new gallery to see how I stylishly combined a latex body from Fetish Fantaisies. Have a glamorous weekend 😘 Lady Vanessa 💋

Sensitive content

Do you also feel this desire for hot latex, the material, the shine, the dominance? I don't want to give too much information but take a look at my new gallery to see how I stylishly combined a latex body from Fetish Fantaisies. Have a glamorous weekend 😘 Lady Vanessa 💋

ᖴᕮTISᕼ DIVᗩ LᗩDY ᐯᗩᑎᕮSSᗩ™

177,068 views • 2 years ago

So happy to share the existence of Creature ( Creature ) today. We have been hard at work on developing a new mixed reality game - more on that in a few months. We also started a VR-focused game label and today we’ve announced our first 3 partner studios. 🧵🪡🧶

So happy to share the existence of Creature ( Creature ) today. We have been hard at work on developing a new mixed reality game - more on that in a few months. We also started a VR-focused game label and today we’ve announced our first 3 partner studios. 🧵🪡🧶

Doug North Cook

15,825 views • 3 years ago

📢📢📢 Excited to share our new work *Autonomous Character-Scene Interaction Synthesis from Text Instruction* (Siggraph Asia 24). It presents a unified model for flexible scene-conditioned motion generation given text, scene, trajectory conditions. The results with smooth interaction look very impressive! 📰Paper: Project: Code and data will be released soon.

📢📢📢 Excited to share our new work Autonomous Character-Scene Interaction Synthesis from Text Instruction (Siggraph Asia 24). It presents a unified model for flexible scene-conditioned motion generation given text, scene, trajectory conditions. The results with smooth interaction look very impressive! 📰Paper: Project: Code and data will be released soon.

Siyuan Huang

11,451 views • 1 year ago

Had an idea last night to test out the Atlas Splitter node and make this paint stroke copper material. It's a similar method that I used to do back at Riot for some of our R&D but a lot simpler. Really like the way it came out for a quick hour or so test.

Had an idea last night to test out the Atlas Splitter node and make this paint stroke copper material. It's a similar method that I used to do back at Riot for some of our R&D but a lot simpler. Really like the way it came out for a quick hour or so test.

Kill the Butcher 🪨⚰️☕️

53,054 views • 2 years ago

We've just posted a new dev blog! In this community update, we cover a bunch of upcoming critter improvements like critter growth and powerful alpha critters. We also share sneak peeks at the work-in-progress ambient audio system and our progress on other immersive features. Check out our full blog for our latest news here!:

We've just posted a new dev blog! In this community update, we cover a bunch of upcoming critter improvements like critter growth and powerful alpha critters. We also share sneak peeks at the work-in-progress ambient audio system and our progress on other immersive features. Check out our full blog for our latest news here!:

Path of Titans

16,487 views • 1 year ago

The Cowboy Code calls us to turn big dreams into deeds done. To do the impossible – and then do it again. The #CowboyFamily is invited to join us on next Thursday for a celebration as we launch a new era at #okstate. The Cowboy Code Rally 🔶 Thursday, Nov. 13 at 10:45 am 🔶 The McKnight Center Plaza 🔶 Block party, food trucks, giveaways Our word is our bond. The Code is our call. How will you answer? Learn more: #TheCodeCalls

The Cowboy Code calls us to turn big dreams into deeds done. To do the impossible – and then do it again. The #CowboyFamily is invited to join us on next Thursday for a celebration as we launch a new era at #okstate. The Cowboy Code Rally 🔶 Thursday, Nov. 13 at 10:45 am 🔶 The McKnight Center Plaza 🔶 Block party, food trucks, giveaways Our word is our bond. The Code is our call. How will you answer? Learn more: #TheCodeCalls

Oklahoma State Univ.

28,824 views • 10 months ago

#WayV's #WINWIN, #KUN, #XIAOJUN arrive on the red carpet at the 2023 tencent entertainment white paper awards kun: this year, we released our second album, thank you so much to wayshennies for your support and for waiting. look forward to our all new 2024 🙂 winwin: very happy to be here 😊 wish everyone a happy, healthy and joyful 2024. also hope everyone can look forward to our stages xiaojun: in 2024, we really made quite a lot of beautiful memories. wish everyone good fortune in 2024 😄 #CPop

#WayV's #WINWIN, #KUN, #XIAOJUN arrive on the red carpet at the 2023 tencent entertainment white paper awards kun: this year, we released our second album, thank you so much to wayshennies for your support and for waiting. look forward to our all new 2024 🙂 winwin: very happy to be here 😊 wish everyone a happy, healthy and joyful 2024. also hope everyone can look forward to our stages xiaojun: in 2024, we really made quite a lot of beautiful memories. wish everyone good fortune in 2024 😄 #CPop

tiff ☕

22,919 views • 2 years ago

My Market Dashboard(Updated) My previous GitHub live site link experienced a sudden traffic surge from X (too popular?)and was flagged as bot activity, leading to a suspension. Without any reply from Github after 10 days, I decided to migrate the entire project to GitLab. Also, I added some new features to it, Multi-chart grid view, ETF Holdings and Market Breadth. The data will be updated automatically Mon–Fri at 16:30 US Eastern. The project is fully open-sourced. You can find the Live Site link and the Source Code on my GitLab homepage(link below). If you’d like to customize it, feel free to fork the repo. For more details, you can watch the demo video below. I'm happy to continue sharing this with the FinTwit community. GitLab homepage:

My Market Dashboard(Updated) My previous GitHub live site link experienced a sudden traffic surge from X (too popular?)and was flagged as bot activity, leading to a suspension. Without any reply from Github after 10 days, I decided to migrate the entire project to GitLab. Also, I added some new features to it, Multi-chart grid view, ETF Holdings and Market Breadth. The data will be updated automatically Mon–Fri at 16:30 US Eastern. The project is fully open-sourced. You can find the Live Site link and the Source Code on my GitLab homepage(link below). If you’d like to customize it, feel free to fork the repo. For more details, you can watch the demo video below. I'm happy to continue sharing this with the FinTwit community. GitLab homepage:

Will Hu

23,691 views • 6 months ago