Associate Prof. @ https://xitter.cf/t.co/YCTONqWlya Previously @HarvardVCG with @hpfister, MPI Informatics with https://xitter.cf/t.co/cGvenfvLqx, @uclcs with @jankautz
Joined May 2011
- Tweets341
- Following296
- Followers1.2K
- Likes679
James Tompkin retweeted
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 @zonkedNGray @volokuleshov @jtompkin
James Tompkin retweeted
Can GANs outperform diffusion models in 2024?
Yes!
#2200: The GAN is dead; long live the GAN! A Modern GAN Baseline! Come join me if you're attending NeurIPS 2024. Thursday evening poster session 4:30-7:30 .
#NeurIPSConference with @zonkedNGray @volokuleshov @jtompkin
Need evaluation and insight into why monocular dynamic scene reconstruction is difficult especially with Gaussian splats? Need apples-to-apples comparison of basic motion models on a scene with controlled camera and object motion? Here you go.
Monocular Dynamic Gaussian Splatting is Fast and Brittle but Smooth Motion Helps
@YiqingLiang2, Mikhail Okunev, @mikacuy, Runfeng Li, Leonidas Guibas, @jtompkin, @AdamWHarley
tl;dr: benchmark for monocular dynamic GS
arxiv.org/abs/2412.04457
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/lgd… First author Xiuchao Wu is graduating soon and is looking for a job!
James Tompkin retweeted
Learn how to interpolate time-of-flight depth videos using Flowed Time of Flight Radiance Fields (F-TöRF) at this morning’s @eccvconf poster session.
Project:
mmehas.github.io/ftorf/
With Mikhail Okunev*, Marc Mapeke*, @imarhombus, @mpotoole, @jtompkin
James Tompkin retweeted
Applications are now open for the Spring '25 iteration of our undergraduate research experience program "exploreCSR: Socially-Responsible Artificial Intelligence!"
explorecsr.cs.brown.edu/ai/i…
James Tompkin retweeted
Brown's Presidential Postdoc Fellowship is now accepting applications for 2025. 2 years of funding. Oct 31st deadline. apply.interfolio.com/153332
James Tompkin retweeted
To kick off SIGGRAPH '24: We're thrilled to announce that @AdrianaSchulz7 will be joining us at Brown starting Fall 2025!
James Tompkin retweeted
🚨 🚨 🚨 The Neural Fields Beyond Conventional Cameras workshop at #ECCV2024 is accepting papers and extended abstracts for poster and oral presentation!
We welcome papers submitted to @eccvconf, whether accepted or rejected.
Deadline: August 9, 2024
Happy to share the 1st Workshop on Neural Fields Beyond Conventional Cameras will be hosted at @eccvconf #ECCV2024 in Milan, Italy!
Webpage: neural-fields-beyond-cams.gi…
Confirmed speakers include @DaveLindell, @jon_barron, Tali Treibitz, and Daniel Cremers, with more coming soon!
James Tompkin retweeted
Job Opportunity! At @BrownUniversity @Brown_DSI I direct the (new) Center for Tech Responsibility (CNTR). I'm looking to hire a Program Manager who would work with me to help operationalize the vision for the Center. If you're interested, apply! brown.wd5.myworkdayjobs.com/…
James Tompkin retweeted
The BVC Seminar will host Ryan Capouellez this Friday (4/5, 12pm EST)! Ryan's talk, "Metric Optimization in Penner Coordinates" will be livestreamed at youtube.com/@brownvisualcomp…! Don't miss it!
James Tompkin retweeted
$2500 awards for underrepresented students to attend CVPR! Funding for travel, conference fees, AND a chance to network with top speakers at our AI4CC workshop. Eligibility not tied to authorship. Apply now! Link to application: docs.google.com/forms/d/e/1F… #Diversity #CVPR2024
James Tompkin retweeted
AI for Content Creation workshop is back at #CVPR2024. 21st March paper deadline @ ai4cc.net. Plus stellar speakers:
@AaronHertzmann
@liuziwei7
@robrombach
@talidekel
@Jimantha
@Diyi_Yang
late breaking speakers and special guest panel
!!!
The AI for Content Creation workshop is back at CVPR 2024 ai4cc.net Top speakers and late-breaking speakers too. Workshop papers (due Mar21st), prizes to win, even travel awards (due Mar15th)!
James Tompkin retweeted
The BVC Seminar is returning this Friday at 12pm EST with a talk from Yotam Gingold @yig ! Yotam's talk, "Color, Shape, and Thought" will be livestreamed on YouTube, hope to see you there!
youtube.com/@brownvisualcomp…
Brown's Visual Computing Group is looking for new PhD students, too - visual.cs.brown.edu - including me - jamestompkin.com
I work at the intersection of vision and graphics, especially work close to real cameras 📸
Applications due tomorrow.
cs.brown.edu/degrees/doctora…
Recent projects!
- Embedding semantics in 4D monocular video for easier editing visual.cs.brown.edu/saff
- Differentiable splatting for depth edge completeness visual.cs.brown.edu/incomple…
- Modeling low-level depth cameras for neural reconstruction (w CMU) imaging.cs.cmu.edu/nfsl
- Modeling optical image stabilization for depth (w KAIST) minhkim.org/eccv2022
- Conditioning generative models so that we don't drop quality when adding control arxiv.org/abs/2305.13460
- Judging if human texture perception is matched in deep learning github.com/brownvc/Slant-CNN…
Have you ever been outside?🏞️I hear it's big🏙️Scaling high detail neural rendering requires efficient parallel optimization of the scene _and_ its cameras📸 #SIGGRAPHAsia2023 - Friday 10:15am in C4.8 in Sydney! xchaowu.github.io/papers/sca… @neural_fields
More great work from Xiuchao Wu (xchaowu.github.io) and Jiamin Xu (superxjm.github.io) led by Weiwei Xu (cad.zju.edu.cn/home/weiweixu…) at Zhejiang University, with Xin Zhang, Hujun Bao, Yujun Shen and @qixing_huang, too.