Dimitrije Antić

CV & ML Ph.D. student @UVA_Amsterdam | prev. @uni_tue @MPI_IS | Teaching machines to perceive humans.

[International Conference on 3D Vision (3DV) @3DVconf]

Looking for a nice home for your paper? #3DV2027 is waiting! 🎉

⏰ Conference dates: April 6-9, 2027
✈️ Place: #Thessaloniki (#SKG), #Greece 🇬🇷

📝 Paper ddl: Aug 28
🎥 Supp ddl: Sep 02
🆕 Rebuttal only upon invite for borderline papers!

#CallForPapers: https://t.co/6Fy3QG7PRE

[François Fleuret @francoisfleuret]

IMO a researcher studies a problem that may not be solvable, while an engineer solves a problem that is considered solvable.

[Sai Kumar Dwivedi @saidwivedi]

Most research time isn’t spent thinking of ideas.

It’s spent checking prior work, testing hypotheses, debugging silent bugs, organizing results, making slides.

The parts where weeks of work silently disappear.

I tried encoding some of that experience as “Agent Skills”.

[Joseph Viviano @josephdviviano]

me: "can you use whatever resources you like, and python, to generate a short 'youtube poop' video and render it using ffmpeg ? can you put more of a personal spin on it? it should express what it's like to be a LLM"

claude opus 4.6:

[Frank Dellaert @fdellaert]

Do not execute yet. Ask clarifying questions until we align and then make a plan on which I sign off.

[Bogdan Bogdanovic @LeaderOfHorde]

Novak Djokovic.

[Pedro Domingos @pmddomingos]

When AI automates parts of your job, it increases the value of the parts it doesn't. I.e., it makes you more valuable.

[Prof. Feynman @ProfFeynman]

If you're stuck, simplify. If you're still stuck, simplify again.

[Catturd ™ @catturd2]

One of these men was banned from Australia.

[Neil Renic @NC_Renic]

Pre-PhD: I have a question

Mid-PhD: I have a headache

[Dimitrije Antić @anticdimi]

@Vinc3nt_Leroy @ICCVConference I believe this is the correct: https://t.co/VJxfQDT1kC

[Dimitrije Antić @anticdimi]

#SDFit will be presented at #ICCV2025:
⏰ 21 Oct, 15:00-17:00
📍 Poster #892

🌐 Webpage: https://t.co/ycmqtp4ODe
👨‍💻 Code: https://t.co/1an77gxjGw

Great collaboration between:
👉 @UvA_Amsterdam → me, @gkpaschalidis, @theogevers, @dimtzionas 👉 @MPI_IS → @saidwivedi, @sha2nk_t
Thanks to reviewers & ACs for feedback!

(6/6🧵)

[Dimitrije Antić @anticdimi]

Intelligent systems need to understand #3D Objects from single images. However, recent SotA methods work well for unoccluded views & common poses, and prioritize shape over pose. We tackle this by developing #SDFit #ICCV2025 a novel Render-n-Compare framework for 3D objects that:
👉 Is robust to occlusion & uncommon poses
👉 Treats both Shape & Pose as 1st class citizens

(1/6🧵)

[Dimitrije Antić @anticdimi]

To conclude:

👉#SDFit exploits an explicit, morphable 3D shape prior (mSDF) to generate 3D hypotheses, and a feedback loop to fit the mSDF hypothesis to an img

👉#SDFit is a good step toward robust 3D perception, and provides insights toward methods that better 'understand' rather than 'hallucinate'

(5/6🧵)

[Yuliang Xiu @yuliangxiu]

depth ambiguity

[Peyman Milanfar @docmilanfar]

Stochastic Gradient Descent