The BVC Seminar will host Ticha Sethapakdi this Friday at 12pm Eastern! Tune in to Ticha's talk, "Engineering Expressive Technologies" live on the BVC YouTube channel

At SIGGRAPH this week? Have opinions on how LLMs should (or shouldn't) be used to review papers? Come discuss at Prof. Ritchie's session on "LLMs in the Technical Papers Review Process"---Weds Aug 13 5pm in East Building Room 15.

Do you have a paper at SIGGRAPH that has result images/videos featuring the SIGGRAPH name and/or logo? Please submit to the SIGGRAPH Logo Gallery! siggraph-logo.gallery

FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation
ivl.cs.brown.edu/research/fou...
A dataset and foundational model for hand images. Tired of weird/malformed hands in your diffusion model outputs? FoundHand can fix them. (7/7)

UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping
aashishrai3799.github.io/uvgs/
Shows how to compress a 3DGS representation of an object into a single RGB image which is amenable to analysis and generation with state-of-the-art image models. (6/7)

Zero-shot Monocular Scene Flow Estimation in the Wild
research.nvidia.com/labs/lpr/zer...
Take any two unposed views of a video and generate 3D points + 3D motion. Trained only on synthetic data, the model generalizes well to casual real-world videos or even robot pick and place. (5/7)

Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
visual.cs.brown.edu/projects/gft...
Models continuous-wave time of flight signals within Gaussian splatting, revealing ways to better optimize GS to converge in underconstrained monocular settings. (4/7)

GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities
ivl.cs.brown.edu/research/gig...
A massive annotated dataset of bimanual hand activities. Opens up new applications in (conditional) hand motion generation, dynamic reconstruction, motion retargeting, and more. (3/7)

Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
bardofcodes.github.io/patterns/
Analogy-based editing in-the-wild pattern images. Now you can take any image of a regular-grid tiling pattern and turn into, say, a radially-tiled version of the same pattern. (2/7)

Check out the Brown Visual Computing papers that will be appearing at CVPR in Nashville this summer: (1/7)

BVC Seminar will host Itai Lang this Friday at 12pm Eastern! Catch his talk, "Clicks and Prompts: Intuitive Interactive Segmentation and Local Editing of 3D Shapes" live on YouTube!

www.youtube.com/@brownvisual...

The AI for Content Creation workshop #CVPR2025 is accepting paper submissions. ai4cc.net Deadline March 21st 2025 midnight PST. 4 page extended abstracts, 8 pagers, and previously published work (ECCV, NeurIPS, even CVPR)! Many topics 📷📹🎬🎲✒️📃🖼️👗👔🏢 - come spend the day with us!

The BVC Seminar will host Jiahui Lei this Friday (3/14, 12pm EST)! Catch Jiahui's talk "4D Vision: Represent, Reconstruct, and Generate the Dynamic 3D World" live on the BVC youtube channel www.youtube.com/@brownvisual...!

Can GANs compete in 2025? In 'The GAN is dead; long live the GAN! A Modern GAN Baseline', we show that a minimalist GAN w/o any tricks can match the performance of EDM with half the size and one-step generation - github.com/brownvc/r3gan - work of Nick Huang, @skylion.bsky.social, Volodymyr Kuleshov

But what if you _really_ like reflections? Local Gaussian Density Mixtures updates lumigraphs by optimizing mixtures of per-view volumes for 🌟maximum shine🌟 #SIGGRAPHAsia2024 xchaowu.github.io/papers/lgdm/... First author Xiuchao Wu is graduating soon and is looking for a job!

Applications are now open for our NSF Summer REU Site, Artificial Intelligence for Computational Creativity!
aireu.cs.brown.edu
Deadline: Feb 3, 2025

The BVC Seminar is excited to host Qixing Huang
tomorrow (11/21, 1pm EST)! Qixing's talk "Geometric Regularizations for 3D Shape Generation" will be livestreamed at www.youtube.com/@brownvisual...