Dimitrije Antić @anticdimi

CV & ML Ph.D. student @UVA_Amsterdam | prev. @uni_tue @MPI_IS | Teaching machines to perceive humans. anticdimi.github.io Joined September 2020

Tweets

253
Followers

312
Following

827
Likes

4K

François Chollet @fchollet

2 weeks ago

Everything happens so much

32 19 338 52K 23

View Details

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

2 weeks ago

#3DV2027 #CallForPapers 3dvconf.github.io/2027/call-for-…

1 10 69 5K 14

View Details

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

2 months ago

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: 3dvconf.github.io/2027/call-for-…

3 22 94 11K 27

View Details

François Fleuret @francoisfleuret

2 months ago

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

Yacine Mahdid @yacinelearning

2 months ago

53 63 2K 479K 212

197 78 2K 298K 289

View Details

Mathieu @miniapeur

4 months ago

4 149 1K 35K 76

View Details

Sai Kumar Dwivedi @saidwivedi

4 months ago

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”.

1 3 12 741 10

View Details

Joseph Viviano @josephdviviano

5 months ago

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:

545 1K 12K 1.5M 7K

View Details

Frank Dellaert @fdellaert

5 months ago

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

3 3 29 6K 14

View Details

Bogdan Bogdanovic @LeaderOfHorde

6 months ago

Novak Djokovic.

72 930 21K 233K 110

View Details

Pedro Domingos @pmddomingos

6 months ago

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

42 20 235 17K 37

View Details

Prof. Feynman @ProfFeynman

7 months ago

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

144 814 6K 198K 1K

View Details

Catturd ™ @catturd2

7 months ago

One of these men was banned from Australia.

2K 37K 240K 19.3M 7K

View Details

Neil Renic @NC_Renic

8 months ago

Pre-PhD: I have a question Mid-PhD: I have a headache

12 195 2K 64K 89

View Details

Dimitrije Antić @anticdimi

9 months ago

@Vinc3nt_Leroy @ICCVConference I believe this is the correct: media.eventhosts.cc/Conferences/IC…

1 0 2 47 0

View Details

Dimitrije Antić @anticdimi

9 months ago

#SDFit will be presented at #ICCV2025: ⏰ 21 Oct, 15:00-17:00 📍 Poster #892 🌐 Webpage: anticdimi.github.io/sdfit 👨‍💻 Code: github.com/anticdimi/sdfit Great collaboration between: 👉 @UvA_Amsterdam → me, @gkpaschalidis, @theogevers, @dimtzionas 👉 @MPI_IS → @saidwivedi, @sha2nk_t Thanks to reviewers & ACs for feedback! (6/6🧵)

0 0 2 163 0

View Details

Dimitrije Antić @anticdimi

9 months ago

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🧵)

1 0 2 130 0

View Details

Dimitrije Antić @anticdimi

9 months ago

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🧵)