Lightnews — Scholar-powered news

Anand Bhattad

@anandbhattad.bsky.social

200 followers 200 following 59 posts

Incoming Assistant Professor at Johns Hopkins University | RAP at Toyota Technological Institute at Chicago | web: https://anandbhattad.github.io/ | Knowledge in Generative Image Models, Intrinsic Images, Image-based Relighting, Inverse Graphics

anandbhattad.github.io

Posts Media Videos Starter Packs

Pinned

Anand Bhattad @anandbhattad.bsky.social · 17d

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...

So You Want to Be an Academic? What I Wish I Knew Early in Graduate School

Blog for junior PhD students on work, visibility, community, and sanity—long before the faculty job market is on the horizon.

anandbhattad.github.io

1 4 20

Anand Bhattad @anandbhattad.bsky.social · 2d

I decided not to travel to #ICCV2025 because it coincides with Diwali (Oct 20). Diwali often falls near the #CVPR deadline window, but this year overlaps with ICCV. I understand it’s hard to avoid all global holidays, but I hope future conferences can keep this in mind when selecting dates.

Anand Bhattad @anandbhattad.bsky.social · 2d

I will be recruiting a few students for Fall 2026. In particular, I will strongly consider a PhD applicant with training in applied/computational mechanics and computer vision/machine learning. If you or someone you know has this background, please contact me.

Anand Bhattad @anandbhattad.bsky.social · Jun 2

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.

1 3

Anand Bhattad @anandbhattad.bsky.social · 17d

So You Want to Be an Academic? What I Wish I Knew Early in Graduate School

Blog for junior PhD students on work, visibility, community, and sanity—long before the faculty job market is on the horizon.

anandbhattad.github.io

1 4 20

Anand Bhattad @anandbhattad.bsky.social · Jun 30

Thanks Andreas and the Scholar Inbox team! This is by far the best paper recommendation system I’ve come across. No more digging through overwhelming volumes and like the blog says, the right papers just show up in my inbox.

Reposted by Anand Bhattad

ML for Science @ml4science.bsky.social · Jun 30

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...

Scholar Inbox: Daily Research Recommendations just for You

Science is moving fast. How can we keep up? Scholar Inbox helps researchers stay ahead by making the discovery of open access papers more personal.

www.machinelearningforscience.de

1 14 27

Anand Bhattad @anandbhattad.bsky.social · Jun 30

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...

Anand Bhattad @anandbhattad.bsky.social · Jan 13

🧵 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...

Anand Bhattad @anandbhattad.bsky.social · Jun 23

This is probably one of the best talks and slides I have ever seen. I was lucky to see this live! Great talk again :)

1 3

Anand Bhattad @anandbhattad.bsky.social · Jun 2

A special shout-out to all the job-market candidates this year: it’s been tough with interviews canceled and hiring freezes🙏

After UIUC's blue and @tticconnect.bsky.social blue, I’m delighted to add another shade of blue to my journey at Hopkins @jhucompsci.bsky.social. Super excited!!

Anand Bhattad @anandbhattad.bsky.social · Jun 2

We will be recruiting PhD students, postdocs, and interns. Updates soon on my website: anandbhattad.github.io

Also, feel free to chat with me @cvprconference.bsky.social #CVPR2025

I’m immensely grateful to my mentors, friends, colleagues, and family for their unwavering support.🙏

Anand Bhattad - Research Assistant Professor

anandbhattad.github.io

Anand Bhattad @anandbhattad.bsky.social · Jun 2

At JHU, I'll be starting a new lab: 3P Vision Group. The “3Ps” are Pixels, Perception & Physics.

The lab will focus on 3 broad themes:

1) GLOW: Generative Learning Of Worlds
2) LUMA: Learning, Understanding, & Modeling of Appearances
3) PULSE: Physical Understanding and Learning of Scene Events

Anand Bhattad @anandbhattad.bsky.social · Jun 2

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.

1 2 7

Reposted by Anand Bhattad

Zhenjun Zhao @ericzzj.bsky.social · May 8

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

2 10

Anand Bhattad @anandbhattad.bsky.social · Apr 29

[2/2] However, if we treat 3D as a real task, such as building a usable environment, then these projective geometry details matter. It also ties nicely to Ross Girshick’s talk at our RetroCV CVPR workshop last year, which you highlighted.

Anand Bhattad @anandbhattad.bsky.social · Apr 29

[1/2] Thanks for the great talk and for sharing it online for those who couldn't attend 3DV. I liked your points on our "Shadows Don't Lie" paper. I agree that if the goal is simply to render 3D pixels, then subtle projective geometry errors that are imperceptible to humans are not a major concern.

1 1

Anand Bhattad @anandbhattad.bsky.social · Apr 15

Congratulations and welcome to TTIC! 🥳🎉

Anand Bhattad @anandbhattad.bsky.social · Apr 2

By “remove,” I meant masking the object and using inpainting to hallucinate what could be there instead.

Reposted by Anand Bhattad

Noah Snavely @snavely.bsky.social · Mar 30

This is really cool work!

Anand Bhattad @anandbhattad.bsky.social · Mar 29

[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

1 1 7

Anand Bhattad @anandbhattad.bsky.social · Apr 2

Thanks Noah! Glad you liked it :)

Anand Bhattad @anandbhattad.bsky.social · Apr 2

[2/2] We also re-run the full pipeline *after each removal*. This matters: new objects can appear, occluded ones can become visible, etc, making the process adaptive and less ambiguous.

Fig above shows a single pass. Once the top bowl is gone, the next "top" bowl gets its own diverse semantics too

Anand Bhattad @anandbhattad.bsky.social · Apr 2

[1/2] Not really... there's quite a bit of variation.

When we remove the top bowl, we get diverse semantics: fruits, plants, and other objects that just happen to fit the shape. As we go down, it becomes less diverse: occasional flowers, new bowls in the middle, & finally just bowls at the bottom.

2 1

Anand Bhattad @anandbhattad.bsky.social · Mar 29

[10/10] This project began while I was visiting Berkeley last summer. Huge thanks to Alyosha for the mentorship and to my amazing co-author Konpat Preechakul. We hope this inspires you to think differently about what it means to understand a scene.

🔗 visualjenga.github.io
📄 arxiv.org/abs/2503.21770

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting

Visual Jenga is a new scene understanding task where the goal is to remove objects one by one from a single image while keeping the rest of the scene stable. We introduce a simple baseline that uses a...

visualjenga.github.io

Anand Bhattad @anandbhattad.bsky.social · Mar 29

[9/10] Visual Jenga is a call to rethink what scene understanding should mean in 2025 and beyond.

We’re just getting started. There’s still a long way to go before models understand scenes like humans do. Our task is a small, playful, and rigorous step in that direction.

Anand Bhattad @anandbhattad.bsky.social · Mar 29

[8/10] This simple idea surprisingly scales to a wide range of scenes: from clean setups like a cat on a table or a stack of bowls... to messy, real-world scenes (yes, even Alyosha’s office).

2 1

Anand Bhattad @anandbhattad.bsky.social · Mar 29

[7/10] Why does this work? Because generative models have internalized asymmetries in the visual world.

Search for “cups” → You’ll almost always see a table.
Search for “tables” → You rarely see cups.

So: P(table | cup) ≫ P(cup | table)

We exploit this asymmetry to guide counterfactual inpainting

1 2

Anand Bhattad @anandbhattad.bsky.social · Mar 29

[6/10] We measure dependencies by masking each object, then using a large inpainting model to hallucinate what should be there. If the replacements are diverse, the object likely isn't critical. If it consistently reappears, like the table under the cat, it’s probably a support.

1 1