Astitva Srivastava

@3DVconf Bark-propagation.

Metric depth gone wild 😎 #3DV2026

@karpathy My favourite moment when you described how @3blue1brown's Manim can be a very useful tool to be used by LLMs for content creation.

Pleasure to come by the YC AI Startup School today! I'm told the recordings will be up "in the coming weeks", I'll link to it then and include the slides. Thank you YC for organizing and bringing together an awesome group of builders! events.ycombinator.com/ai-sus Fun fact is that when I (and all the original founding members) decided to join OpenAI, the name OpenAI didn't exist - we all thought we were joining a new AI non-profit under YC Research. My very first OpenAI swag t-shirt says "YC AI Day 1". Things changed up a bit after that. Cheers to YC! :)

@hjessmith Very cute demo! Congratulations. 🎉🥳

Excited to share that our demo, Animating MetaGen Stickers, has been accepted to the demo track of #CVPR2025! Come say hello and play around with the demo yourself if you're attending CVPR! We'll be set up June 13th in the afternoon session.

@jon_barron @Michael_J_Black But how can one even prove that a review is AI-generated? Should I reach out to the AC and request a careful reading of the paper to highlight that the reviews are incoherent or misaligned with the content?

@Michael_J_Black I would just escalate to the PCs and try to get the reviewer ejected from the community, this has happened before in CVPR-land.

How do you rebut an AI-generated review? (This is not hypothetical -- I'm facing this now with ICCV reviews) When writing a rebuttal, I try to understand my reviewer. What do they know? What don't they know? What's annoying them? What do they really care about? But if a person submits an AI review, then I'm at a loss. Have they even read my paper? Have they read the AI review? What kind of person does this? Let's say I carefully rebut the points the AI brought up. What will the reviewer do with this information? They will have no context with which to understand it. Will they feed it to the AI? Why? My guess is that if they didn't bother to write a review themselves, they won't bother to read my rebuttal. All I know about my reviewer is that they are lazy and couldn't be bothered to read my paper, which I labored over, and give me their thoughts. I think the only proper response is to just not reply to their review at all. Or maybe I should give the review to an AI and ask it to write the rebuttal. Tit for tat. PS: Yes, I'm certain the review is AI generated. It is obvious. Bland and wordy with lots of **emphasis**. I ran it through an AI detector and it's rated as 100% AI.

LightHeadEd also supports text-driven appearance editing.

The head avatars obtained using LightHeadEd can be easily edited, both in terms of appearance and geometry.

🚨 Introducing "LightHeadEd" 🚨 📱 Relightable, Editable, Animatable 3D Head avatars — using a Smartphone + Polaroid Filters! ✨Hybrid "Textured Gaussian Head" representation ⚡️ Real-time rendering 🎨 Shape & appearance editing 🔗 Project Page: raipranav384.github.io/lightheaded-we… @PranavRai384 @PJNarayanan @jampani_varun @iiit_hyderabad #GaussianSplatting #Graphics #Metaverse #VirtualReality #GenAI #Research

@lexfridman @narendramodi "Frid-Man ki baat".

I will be doing a podcast with Narendra Modi (@narendramodi), Prime Minister of India, at the end of February. I've never been to India, so I'm excited to finally visit and experience many facets of its vibrant, historic culture and its amazing people as fully as I can.

@MattNiessner Congrats! 🥳

Official promotion to 𝐅𝐮𝐥𝐥 𝐏𝐫𝐨𝐟𝐞𝐬𝐬𝐨𝐫 🥳🥳🥳 Thanks so much to everyone who has been with me on this exciting journey, in particular my amazing PhD students, PostDocs, collaborators, every other supporter! Let's see what's next - just getting started :)

@dancasas Thank you! 🙂

@sarcastitva Very nice! Congrats!

Introducing "WordRobe", a method for Text-Guided Generation of Textured 3D Garments. 👕🥼👚👖 Project Page: wordrobe24.github.io/WordRobe_Page arXiv: arxiv.org/abs/2403.17541 (Unroll 👇) #GenerativeAI #3dmodeling #TextToImage

@Michael_J_Black @eccvconf Thanks! 😇 Kudos to @PranavRai384 for coming up with the title! 👏🏻

@sarcastitva @eccvconf Love the name :)

Excited to announce that "WordRobe" is accepted ✅ at #ECCV2024 (@eccvconf ) 🚀🚀🚀🚀🚀

@Michael_J_Black @_lilyzen FYI, we borrowed this technique from one of your works HOOD. 🤗

@Michael_J_Black @_lilyzen @eccvconf Thanks for pointing out. 🙌🏻 Transferring skinning weights using k-nearest neighbor interpolation doesn't produce plausible deformations in case of loose garments (e.g. skirt). But it gives a decent initialization, after which physics simulation takes over and refines it.