So You Want to Be an Academic? A couple of years into your PhD, but wondering: "Am I doing this right?" Most of the advice is aimed at graduating students. But there's far less for junior folks who are still finding their academic path. My candid takes: anandbhattad.github.io/blogs/jr_gra...

On our blog: Science is moving fast. How do we keep up? #ScholarInbox, developed by the Autonomous Vision Group led by @andreasgeiger.bsky.social, helps researchers stay ahead - by making the discovery of #openaccess papers smarter and more personal: www.machinelearningforscience.de/en/scholar-i...

All slides from the #cvpr2025 (@cvprconference.bsky.social ) workshop "How to Stand Out in the Crowd?" are now available on our website: sites.google.com/view/standou...

I’m thrilled to share that I will be joining Johns Hopkins University’s Department of Computer Science (@jhucompsci.bsky.social, @hopkinsdsai.bsky.social) as an Assistant Professor this fall.

FastMap: Revisiting Dense and Scalable Structure from Motion Jiahao Li, Haochen Wang, @zubair-irshad.bsky.social, @ivasl.bsky.social, Matthew R. Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich tl;dr: replace BA with epipolar error+IRLS; fully PyTorch implementation arxiv.org/abs/2505.04612

This is really cool work!

[1/10] Is scene understanding solved? Models today can label pixels and detect objects with high accuracy. But does that mean they truly understand scenes? Super excited to share our new paper and a new task in computer vision: Visual Jenga! 📄 arxiv.org/abs/2503.21770 🔗 visualjenga.github.io

I can’t believe this! Mind-blowing! There are small errors (a flipped logo, rotated chairs), but still, this is incredible!! Xiaoyan, who’s been working with me on relighting, sent this over. It’s one of the hardest examples we’ve consistently used to stress-test LumiNet: luminet-relight.github.io

Check out UrbanIR - Inverse rendering of unbounded scenes from a single video! It’s a super cool project led by the amazing Chih-Hao! @chih-hao.bsky.social is a rising star in 3DV! Follow him! Learn more here👇

Can we create realistic renderings of urban scenes from a single video while enabling controllable editing: relighting, object compositing, and nighttime simulation? Check out our #3DV2025 UrbanIR paper, led by @chih-hao.bsky.social that does exactly this. 🔗: urbaninverserendering.github.io

Introducing DaD (arxiv.org/abs/2503.07347), a pretty cool keypoint detector. As this will get pretty long, this will be two threads. The first will go into the RL part, and the second on the emergence and distillation.

Last was an intriguing talk by @anandbhattad.bsky.social on the degree to which physical properties are encoded in generative image models at the @grasplab.bsky.social www.youtube.com/watch?v=Idcb... (7/7)

ZeroComp will be presented as an Oral at #WACV2025! Train a diffusion model as a renderer that takes intrinsic images as input. Once trained, we can perform zero-shot object compositing & can easily extend this to other object editing tasks, such as material swapping. arxiv.org/abs/2410.08168

LumiNet is going to be at #CVPR2025! Excited about this work—fully data-driven, with zero reliance on computer graphics datasets. It builds upon our previous works—StyLitGAN provided the training data, while Latent Intrinsics abstracted lighting and albedo for diffusion models. And more to come! 🤓

Really excited to put together this #CVPR2025 workshop on "4D Vision: Modeling the Dynamic World" -- one of the most fascinating areas in computer vision today! We've invited incredible researchers who are leading fantastic work at various related fields. 4dvisionworkshop.github.io

New paper about pictures: I identify trends in geometric perspective in my own drawings and photos, and compare them to how the original scenes looked. I discuss what these trends might say about art history and vision science. Published in _Art & Perception_. #visionscience psyarxiv.com/pq8nb

Encouraging to see a civilized & thoughtful discussion on a few papers in my AC batch. We need more reviewers like this! Also chasing down a few reviewers to update their justification beyond 'my concerns were not addressed in the rebuttal, so I’ll maintain my original score.' 😅 #CVPR2025

Not a big fan of Borderline ratings in the review process. They offer an easy way for reviewers to be non-committal—or even lazy. I’ve never liked this, as it rarely adds value. Clear, decisive ratings with concrete justifications of a paper’s contributions are far more constructive. #CVPR2025

It's great to see renewed interest in Barrow and Tenenbaum's seminal 1978 work on "Intrinsic Images." This foundational paper has significantly influenced the field, even though it has historically received fewer citations than it deserves.

Scholar Inbox provides the best paper recommendations—I rarely miss papers relevant to my interests or related to my work. I wish this could be integrated with paper submission services to flag missing related works.

🧵 1/3 Many at #CVPR2024 & #ECCV2024 asked what would be next in our workshop series. We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup! 🔗 sites.google.com/view/standou...

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

[1/2] Latent Intrinsics Emerge from Training to Relight. We discovered an easy way to extract albedo without any albedo-like images. By questioning why intrinsic image representations must be 3-channel maps, we trained a simple relighting model where intrinsics & lighting are latent variables.

[1/3] From a single image to the 3D world—it’s possible with the right data, & we have it for you🚀 We’re thrilled to release our 360° video dataset. Training a simple conditional diffusion model with explicit camera control can synthesize novel 3D scenes—all from a single image input! #NeurIPS2024

I've never seen a more polished paper teaser video than this one. The 3D Gaussians even cast shadows! fnzhan.com/Evolutive-Re...

Spotlight Poster #NeurIPS2024 📍 East Exhibit Hall A-C, #1500 🗓️ Wed 11 Dec, 16:30 – 19:30 PT Latent Intrinsics: Intrinsic image representation as latent variables, resulting in emergent albedo-like maps for free. Code is now available: github.com/xiao7199/Lat... arXiv: arxiv.org/abs/2405.21074

I'm super stoked to share LumiNet! 🎉 💡LumiNet combines latent intrinsic representations with a powerful generative image model. It lets us relight complex indoor images by transferring lighting from one image to another. It is completely data-driven: no labels, mark-up, not even depth or normals.

Our latest work is on arXiv now and the thread is updated with the movies :) arXiv: arxiv.org/abs/2412.00177 project: luminet-relight.github.io

💡Introducing ScribbleLight, a generative model that can relight an image with simple scribbles - making it easier for virtual staging and interior design of homes. Led by Jun-Myeong, collabs with Anand (TTIC), Pieter (W&M), and Annie. @unccs.bsky.social 👉 chedgekorea.github.io/ScribbleLight/

I'm super stoked to share LumiNet! 🎉 💡LumiNet combines latent intrinsic representations with a powerful generative image model. It lets us relight complex indoor images by transferring lighting from one image to another. It is completely data-driven: no labels, mark-up, not even depth or normals.