Francis Williams (@frncswllms) 's Twitter Profile
Francis Williams

@frncswllms

Senior research scientist at @NVIDIAAI working on 3D representations for geometric deep learning. PhD in ML, Vision, and Graphics from NYU. Opinions are my own.

ID: 800790709599014912

linkhttp://fwilliams.info calendar_today21-11-2016 19:59:17

484 Tweet

2,2K Takipçi

1,1K Takip Edilen

Francis Williams (@frncswllms) 's Twitter Profile Photo

fVDB got mentioned in Forbes! Small correction: fVDB doesn't stand for "framework volumetric data blocks"! Though I kind of love Volumetric Data Blocks and am going to try and find a place to use this. fVDB is the core building block for deep learning on large-scale

Francis Williams (@frncswllms) 's Twitter Profile Photo

🚨 New Version of point-cloud-utils (0.31.0): - M1 Mac wheels finally build correctly and work (see screenshot) - Fix issue where remove_duplicate_vertices created degenerate faces - Save PLY colors as uint8 so they are visible in meshlab - Documentation updates

🚨 New Version of point-cloud-utils (0.31.0):
 - M1 Mac wheels finally build correctly and work (see screenshot)
 - Fix issue where remove_duplicate_vertices created degenerate faces
 - Save PLY colors as uint8 so they are visible in meshlab
 - Documentation updates
David Levin (not the hockey player) (@diwlevin) 's Twitter Profile Photo

The NVIDIA HiFi Physics team is looking for interns with interest/skills in 1⃣ Physics simulation (solids/fluids/differentiable etc) 2⃣ Digital Humans 3⃣ Neural Rendering/Geometry, Video Models 4⃣ Monte Carlo Methods 5⃣ Digital Fabrication Apply: nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAEx…

Francis Williams (@frncswllms) 's Twitter Profile Photo

Twitter is becoming a bit too fascist for my taste but it’s still useful for academic papers. I’m going to start cross posting here and on Threads. Follow me at threads.net/@frncswllms

Yanke Song (@yannnke) 's Twitter Profile Photo

New #NVIDIA paper to make diffusion models better and faster 🚀 Multi-Student Distillation! We distill diffusion models into multiple 1-step students, allowing (a) improved quality by specializing in subsets and (b) improved latency by distilling into smaller architectures. 1/n

New #NVIDIA paper to make diffusion models better and faster 🚀 Multi-Student Distillation!

We distill diffusion models into multiple 1-step students, allowing (a) improved quality by specializing in subsets and (b) improved latency by distilling into smaller architectures.

1/n
Ruilong Li (@ruilong_li) 's Twitter Profile Photo

Ironic to see how self-contradictory this is by first pointing out the nationality of the student then adding a note to explain, because neither of them are necessary in this slide.

Angela Dai (@angelaqdai) 's Twitter Profile Photo

Excited to announce ScanNet++ v2!🎉 Chandan Yeshwanth and Yueh-Cheng Liu have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR & iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ Matthias Niessner kaldir.vc.in.tum.de/scannetpp