George Kopanas @GKopanas Twitter profile

Pinned Tweet

George Kopanas

1 year

We will be in @siggraph 2023 with "3D Gaussian Splatting for Real-Time Radiance Field Rendering", have you ever seen radiance fields with 100+ FPS and MipNeRF360 quality? Check out our website here:

13

147

822

Last Seen Profiles

@StreamOnMax

@MaverickFurst

@KamChancellor

@ultimatefctv

@Acosta

@AnnaKubista

@Onua_tf

@BAM_Brooklyn

@priyankap_patel

@TheSafeAnnaAnon

@IlhanMN

@stw_pdg

@dreads_and

@NikilisRBX

@CyberCrimeRck

@farisbudik

@MikaelThalen

@Dxn_xo

@labovitz

@yuka_yuka_labo

@TMHSBaseball

@PeteKnow_

@echepaalla

@devoanderson_

@om_Reouf

@Tahir_Akyurek

@ijuliets

@stinkyhuggies

@stw_pdg

@KoutaNakachi

@Walgreens

@raviubha

@V_over_M

@NickAlston_cm1

@SheffieldPhil

@Mariskax_Prod

George Kopanas

@GKopanas

10 months

Finally we are releasing the code for "3D Gaussian Splatting for Novel View Synthesis" that won the #SIGGRAPH2023 best paper award. This is a huge milestone and we did a huge effort to provide clean code and reproducible results.

GitHub - graphdeco-inria/gaussian-splatting: Original reference implementation of "3D Gaussian...

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering" - graphdeco-inria/gaussian-splatting

github.com

3

86

500

George Kopanas

@GKopanas

8 months

The most important factor that determines the quality of a reconstruction is not the actual NeRF variant you are using but rather where you place the cameras. We give insights on practical ways to solve this problem in realistic environments.

3

30

229

George Kopanas

@GKopanas

7 months

Between thesis writing and exciting research projects, I managed to prepare the code and the website of my recent paper: "Improving NeRF Quality by Progressive Camera Placement for Free-Viewpoint Navigation" Check it out here:

George Kopanas

@GKopanas

8 months

The most important factor that determines the quality of a reconstruction is not the actual NeRF variant you are using but rather where you place the cameras. We give insights on practical ways to solve this problem in realistic environments.

3

30

229

2

28

197

George Kopanas

@GKopanas

8 months

3D Gaussians shipped in @Polycam3D one of the most popular 3D reconstruction softwares! It's like seeing your little kid go to college 🥹

polycam

@Polycam3D

8 months

Big news - we shipped Gaussian Splatting 🎉 Capture the impossible at: 🔥 Processing is free, and splats render fast in the browser. You can also export the .ply file. Enjoy 🚀

72

451

3K

6

10

178

George Kopanas

@GKopanas

3 months

Yup, this week was my first week outside academia for a long time. I decided to join forces with @jon_barron and all the other great folks in his team. Hopefully together we will manage to find the optimal way to represent 3D scenes. I will be in London for the imminent future!

Jon Barron

@jon_barron

3 months

This week @GKopanas (of 3DGS fame) joined our team at Google! Everyone is thrilled to have him here, and I'm very excited to see what we can do together. Pictured: Bard's rendition of "a Neural Radiance Field and 3D Gaussians giving each other a high-five."

7

6

175

11

2

160

George Kopanas

@GKopanas

2 years

I am happy to announce that our paper "Neural Point Catacaustics" got accepted into SIGGRAPH Asia 2022. On our website, you will find all our material, including a full video and a pre-print. 1/4

2

28

114

George Kopanas

@GKopanas

9 months

If you find dynamic NeRFs cool, check out this work where we exploit some of the very interesting properties of the 3D Gaussian Splatting for persistent tracking through time. We learned a lot working with @JonathonLuiten that helped us understand better the power of 3DGS.

Jonathon Luiten

@JonathonLuiten

9 months

Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis We model the world as a set of 3D Gaussians that move & rotate over time. This extends Gaussian Splatting to dynamic scenes, with accurate novel-view synthesis and dense 3D trajectories.

24

368

2K

2

11

96

George Kopanas

@GKopanas

8 months

That is just beautiful! I promise to open source all my projects such that the community can make things like that…

Alex Carlier

@alexcarliera

8 months

Another experiment with Gaussian Painters ✨🎨 By optimizing 3D Gaussian Splattings over separate images at several viewpoints, it is possible to get a Steganography effect! Three paintings are hidden in those gaussian splats

21

224

1K

3

2

89

George Kopanas

@GKopanas

7 months

📢 My lab, GraphDeco, is hiring a software engineer to work on 3D Gaussian Splatting. We want to improve our method and incorporate ideas that span between research and engineering. We need experience in Graphics APIs and good programming skills. Send me a DM/drop me an email.

2

12

84

George Kopanas

@GKopanas

6 months

Super interesting idea, let's find now a way to create the minimum amount of points necessary 🥲

Linus Franke

@_linus_franke

6 months

Introducing our paper "VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural Rendering" ( @SIGGRAPHAsia 2023). Completing point clouds by lifting 2D visual error maps for photo realistic rendering. 📖: 📜:

5

36

229

1

4

71

George Kopanas

@GKopanas

9 months

Dogos and 3D Gaussian Splatting? Worth all the hardships of my PhD :D

Infinite-Realities

@8Infinite8

9 months

Meet our inhouse tech Doggo "Rolo". Cinematic RGB Lighting "More Doggo than Doggo" Since July we've been redesigning our scanning pipeline to work with the amazing 3D Gaussian Splatting for Real-Time Radiance Field Rendering method from Inria. IR's…

23

129

796

4

7

64

George Kopanas

@GKopanas

9 months

Super cool to see our method working well in these challenging datasets.

Hugues Bruyère

@smallfly

9 months

I finally managed to run some of my own datasets with '3D Gaussian Splatting for Real-Time Radiance Field Rendering'. Here is the first one, rendered in real-time. The output is incredible! More to come. #AI #NeRF #gaussiansplatting #radiancefield #Computervision

5

33

342

1

57

George Kopanas

@GKopanas

9 months

Getting a #SIGGRAPH2023 paper and getting memed? Best day of my life. Come tomorrow morning to our talk at 10:45 in room 502AB. We have special real time demos prepared for you.

Jia-Bin Huang

@jbhuang0604

9 months

Paper summary:

3

31

230

1

0

53

George Kopanas

@GKopanas

5 months

Well, there is no holy grail in science. Check out this amazing work. The quality is insane and it works on mobile too! Kudos to everyone involved!

Daniel Duckworth

@duck

5 months

Introducing SMERF: a streamable, memory-efficient method for real-time exploration of large, multi-room scenes on everyday devices. Our method brings the realism of Zip-NeRF to your phone or laptop! Project page: ArXiv: (1/n)

19

191

875

2

1

50

George Kopanas

@GKopanas

1 month

One of the fair criticisms regarding 3DGS was the size of the representation. @PapantonakisP did a great job dealing with it. Great pleasure to work with him on this!

PanagiotisP

@PapantonakisP

1 month

With our work "Reducing the Memory Footprint of 3D Gaussian Splatting," a method that reduces the size of 3DGS from several hundreds to just a few tens of MBs, you now have more space available for additional scenes! For more, check out our project page

2

42

214

2

0

49

George Kopanas

@GKopanas

7 months

Wait!?! Is this the loading effect of @LumaLabsAI in real life?

Culture Critic

@Culture_Crit

7 months

The lights show at the Notre-Dame de Reims is spectacularly beautiful. Reims Cathedral is where kings of France once went to be crowned - the cathedral has hosted 33 coronations in its history. In 498, Clovis King of the Franks was baptized at Reims, making him the West's first…

210

2K

13K

2

0

44

George Kopanas

@GKopanas

5 months

My supervisor G.Drettakis is looking for Master Students to work on topics that extend between Graphics, 3D Reconstruction, and of course Gaussian Splatting. Feel free to apply if you are a MSc student and you look for a thesis

1

5

41

George Kopanas

@GKopanas

1 year

We completely shift the paradigm from voxel-based representations to a point-cloud representation and achieve top quality with extremely fast rendering and training.

3

5

39

George Kopanas

@GKopanas

8 months

Awesome blogpost with some very refreshing references that I wasn't aware of!

Gaussian Splatting is pretty cool! · Aras' website

aras-p.info

jendrik illner

@jendrikillner

8 months

Graphics Programming weekly - Issue 304 - September 10th, 2023

1

68

245

1

4

39

George Kopanas

@GKopanas

1 year

For more info visit our website, and shoutout to my collaborators @Snosixtytwo , Thomas Leimkühler, and George Drettakis.

2

3

40

George Kopanas

@GKopanas

8 months

Super amazing stuff from the community!!

Markus Schütz

@m_schuetz

8 months

Awesome browser-based gaussian splat implementation by @jakub_c5y :

7

50

282

1

3

31

George Kopanas

@GKopanas

5 months

Can't agree more that we need more scalable representations that generative models can handle efficiently. Check this out:

Lior Yariv

@YarivLior

5 months

Thrilled to share Mosaic-SDF (M-SDF), a simple 3D representation suitable for 3D generative models! Check out more results of text-to-3D generations here -

9

72

472

0

1

29

George Kopanas

@GKopanas

26 days

A very nice take on replacing the heuristics of 3DGS with something more principled + a huge boost in numbers. Way to go @Shakiba_kh , Daniel Rebain and all the rest!

Andrea Tagliasacchi 🇨🇦🏔️

@taiyasaki

26 days

📢📢📢 3D Gaussian Splatting brought you real-time rendering, but at slightly lower PSNR compared to mipNeRF360... 𝐚𝐬 𝐨𝐟 𝐭𝐨𝐝𝐚𝐲, 𝐭𝐡𝐚𝐭 𝐢𝐬 𝐧𝐨 𝐥𝐨𝐧𝐠𝐞𝐫 𝐭𝐫𝐮𝐞. Introducing "3D Gaussian Splatting as Markov Chain Monte Carlo"

10

25

257

0

28

George Kopanas

@GKopanas

1 month

What a cool result. Many projects have tried this auto regressive idea of generating and inpainting but the execution here is amazing. Amazing job from the whole team

Alex Trevithick

@alextrevith

1 month

Check out RealmDreamer ()--our new 3D scene generation method! No multiview data required :) One of my favorites is this: "Fantasy lighthouse in the Arctic, surrounded by a world of ice and snow, shining with a mystical light under the aurora borealis."

1

10

63

0

3

28

George Kopanas

@GKopanas

10 months

Great work from the original NeRF team. So happy to see radiance fields become more and more robust in diverse scales and environments! @jon_barron how many input views are we talking about here?

Jon Barron

@jon_barron

10 months

Our freshly minted ICCV2023 paper: The nice anti-aliasing of mip-NeRF 360, but with most of the speed of Instant NGP. Error rate reductions of 8%-77% compared to either prior technique, and 24x faster than the most accurate NeRF baseline we tried.

16

93

692

1

28

George Kopanas

@GKopanas

9 months

Loved the explanation part! I can now show it to my mom!

dylan

@dylan_ebert_

9 months

a two minute explanation of 3D Gaussian Splatting

48

384

2K

0

1

26

George Kopanas

@GKopanas

1 year

Making NeRFs easy to edit is one step towards getting them widely adopted. Proud to work with the very much talented @clementjbn for this. Also the code is out and is built on top of @NVIDIAAI instantNGP. The main motivation is to make it easy for casual users so give it a try!

Clément Jambon

@clementjbn

1 year

📢 I am happy to share our paper "NeRFshop: Interactive Editing of Neural Radiance Fields" 🎨, to be presented at I3D 2023! 🌐: 🎥: 1/6

8

96

396

0

4

25

George Kopanas

@GKopanas

7 months

I usually try not to share gaussian splats. By ooh my...that looks clean!

Alex Carlier

@alexcarliera

7 months

New 3D Gaussian Splatting recording! Those metallic reflections and leather were captured REALLY well! When looking closer, you can also see how the watch hands are modeled with just a couple of elongated gaussians. #GaussianSplatting

19

70

751

0

3

23

George Kopanas

@GKopanas

9 months

There are so many cool papers through the whole history of computer vision and graphics. I am happy to give shoutouts to the ones that could not make it to our related work section!

Pascal Fua

@FuaPv

9 months

The recent 3D Gaussian Splatting paper triggered a bout of nostalgia. In the 1990s, inspired by an earlier @szeliski paper, I had played with the idea of using "particles". Similar to splats and worked quite well ... without deep learning ;-)

0

7

83

1

0

23

George Kopanas

@GKopanas

10 months

That is a very very cool result. Check it out! Thanks @henrypearce4D for sharing.

Henry Pearce

@henrypearce4D

10 months

Testing out @siggraph 2023 Best paper : 3D Gaussian Splatting for Real-time Radiance Field Rendering at Infinite-Realities with a head scan from our datasets by @triplegangers It's rendering at over 120fps! #SIGGRAPH2023 @8Infinite8

4

21

122

0

1

20

George Kopanas

@GKopanas

9 months

@jon_barron I am getting a bit sad seeing people get polarized and trying to pick sides. Thank you for not doing this and, I wish as a community we discuss more about the graphics representations, in a world where inverse rendering is a primal way to create 3d assets.

3

0

20

George Kopanas

@GKopanas

2 months

@janusch_patas Well, I would consider this plain plagiarism of the original code-base. Not very academic to take a code base, copy paste half of it add a couple of new features and slap a new licence on it.

1

0

19

George Kopanas

@GKopanas

9 months

@pfau Btw, I would not consider our method contradictory to NeRFs, the term is heavily ambiguous nowadays and we are heavily reusing the image formation model of NeRFs, so even if our method is not neural is pretty much an approximation of volumetric rendering through rasterization.

1

0

16

George Kopanas

@GKopanas

8 months

Perspective and artistic expression is a very interesting topic, and excellently delivered by @AaronHertzmann Thank you for sharing it on YouTube :)

How Do We Perceive Perspective in Pictures?

How do people interpret 3D space and perspective in pictures? Linear perspective, developed in the Renaissance, is taught in art and in computer graphics, bu...

www.youtube.com

0

1

16

George Kopanas

@GKopanas

1 year

@Rafael_L_Spring @siggraph A) We explicitly model view-dependent effects using spherical harmonics, it's a common trick used in other works too (check Plenoxels, very inspiring work). B) This is on-point, one would need to maintain meaningful gradients but possibly could scale the method even more.

0

1

15

George Kopanas

@GKopanas

10 months

@docmilanfar @siggraph @Snosixtytwo It is embarrassingly beautiful to read these nice words for your work from researchers that you look up to. This is what academia and conferences is all about, it's worth all the hardships of doing a PhD. Thank your for taking the time publicly discuss our research.

1

0

15

George Kopanas

@GKopanas

1 year

"Neural Point Catacaustics" code is out: In other news, next week, I am heading to #SIGGRAPHAsia2022 and I am going to present "Neural Point Catacaustics". Feel free to come to talk to me, I look forward to my first in-person conference as a Ph.D. student

George Kopanas

@GKopanas

2 years

I am happy to announce that our paper "Neural Point Catacaustics" got accepted into SIGGRAPH Asia 2022. On our website, you will find all our material, including a full video and a pre-print. 1/4

2

28

114

0

4

13

George Kopanas

@GKopanas

8 months

If you want to capture an object-centric scene, the solution is simple, just place cameras uniformly around the object. We generalize this empirical observation to complicated scenarios. This is a first step to a problem that we should focus more energy if we want better NeRFs.

1

0

13

George Kopanas

@GKopanas

8 months

Wait, there is more cool stuff other than NeRFs?

David Jourdan

@dJourdan_

8 months

Our paper "Shrink & Morph: 3D-printed self-shaping shells actuated by a shape memory effect" was accepted to SIGGRAPH Asia! We print flat plates with controlled trajectories so that, when heated, they morph into pre-programmed shapes

3

12

56

0

13

George Kopanas

@GKopanas

5 months

@jbhuang0604 My Christmas reading book list is not happy.

0

11

George Kopanas

@GKopanas

1 year

If you participate in #I3D today, don't miss the first presentation of the day, it's NeRFShop! It's the outcome of @clementjbn 's research internship in GraphDeco - Inria.

Clément Jambon

@clementjbn

1 year

📢 I am happy to share our paper "NeRFshop: Interactive Editing of Neural Radiance Fields" 🎨, to be presented at I3D 2023! 🌐: 🎥: 1/6

8

96

396

0

5

11

George Kopanas

@GKopanas

5 months

@taiyasaki In 2023 if the code is not out is because the authors believe that is hard to reproduce. Hard enough that by not releasing it gives them the opportunity to monetize it. I respect that but this means that in most cases reproducing is so hard that is not a reasonable request.

1

0

10

George Kopanas

@GKopanas

7 months

@PMel3D Indeed, it allows training to "cheat" in some cases by hiding gaussians behind other gaussians

0

8

George Kopanas

@GKopanas

2 years

We model this phenomenon using a Neural Warp Field and point clouds. We outperform all state-of-art methods like MipNeRF, InstantNGP, and others. Our method can also render at ~5fps with OpenGL. 4/4

1

0

9

George Kopanas

@GKopanas

1 month

@m_schuetz And the source of impostor syndrome for graphics practitioners across the world.

1

0

9

George Kopanas

@GKopanas

7 months

@alexcarliera 3DGS is doing some heavy lifting but your capture setup is pretty good too! Kudos! Mind sharing some details on how you captured it?

2

0

9

George Kopanas

@GKopanas

8 months

@jongranskog I feel like its the new Doom. Who is gonna make it work on my fridge?

2

0

9

George Kopanas

@GKopanas

10 months

Shout-out to the organizers for sharing the talks through the website of the event. It's very valuable and more workshops and conferences should go into the habit of doing that. Kudos!

Andrea Tagliasacchi 🇨🇦🏔️

@taiyasaki

10 months

We have had an _amazing_ week in Banff at the BIRS “3D Generative Models” workshop Thank to @BIRS_Math for hosting us!

4

19

135

1

0

8

George Kopanas

@GKopanas

3 months

@jon_barron @maciejhalber Splats are Gaussians after someone actively grabs them and throws them to a wall

0

8

George Kopanas

@GKopanas

7 months

Unfortunately, we cannot release the used scenes because of their license terms. In retrospect, I should have considered using less photorealistic scenes but with better license terms to accommodate the research community.

0

7

George Kopanas

@GKopanas

9 months

@Rafael_L_Spring One of the main contributions of the paper is the fact that we render with rasterization. But 3D Gaussians as a representation of the volume are not tightly coupled with rasterization. One could use ray casting if needed 😅

1

0

7

George Kopanas

@GKopanas

10 months

I would like to thank everyone that showed interest to read our paper and sent us questions and extremely insightful comments. I would also like to express my gratitude to the @siggraph committee that honored us with the best paper award among such great papers.

1

0

6

George Kopanas

@GKopanas

7 months

@janusch_patas @LumaLabsAI Seriously, I was scrolling twitter and was waiting for the holes to fill in! 😂

0

6

George Kopanas

@GKopanas

7 months

@TaviusKoktavy @quadjr @arkba @kfarr Seems like something is off. The quality has regressed significantly from the original.

2

0

6

George Kopanas

@GKopanas

10 months

@taiyasaki Thank you, it means a lot! Congratulations to everyone involved @Snosixtytwo , Thomas Leimkhueler and George Drettakis. It's humbling being awarded among such incredible research works that is featured in this year's @siggraph !

2

0

6

George Kopanas

@GKopanas

7 months

@theopanag7 Let's make sure now we can consistently produce this quality results no matter the camera placement 💪💪

0

6

George Kopanas

@GKopanas

8 months

👀👀

Charlie Shenton

@charshenton

8 months

Gaussian Splatting in VR, all code written by me from scratch on DX12 + OpenVR. 2x2016x2240 res, no clever multi-view stuff yet so just running the whole render pipeline once per eye. Left the frame timer on so you can see I've been truthful about my perf :D

34

154

1K

1

0

6

George Kopanas

@GKopanas

2 years

View-dependent effects pose a substantial challenge for image-based and neural rendering algorithms. We introduce a new point-based representation to allow novel-view synthesis with curved reflectors. 2/4

1

0

6

George Kopanas

@GKopanas

2 years

For a planar reflector, a reflected point P results in a static virtual point P', independent of the camera. For curved reflectors, camera motion leads to P' tracing the Catacaustic Surface(CS). The envelope of virtual reflected rays defines the CS for a single point P. 3/4

1

0

5

George Kopanas

@GKopanas

7 months

@aras_p @MartinNebelong @edankwan I am not lawyer either, but rather a main authors of 3DGS. I think viewers that are written from scratch would not have any problems. The asterisk goes regarding how the ply files weere originally created. If the original training code was used the non commercial clause applies.

1

0

3

George Kopanas

@GKopanas

8 months

@m_schuetz @jakub_c5y @Snosixtytwo It is indeed incredible

0

5

George Kopanas

@GKopanas

8 months

@cpheinrich @Polycam3D Let's build big datasets and give the community all the tools to take this a step further!

1

0

5

George Kopanas

@GKopanas

1 year

Thank you, AK!😊

AK

@_akhaliq

1 year

Neural Point Catacaustics for Novel-View Synthesis of Reflections abs: project page:

2

20

134

0

5

George Kopanas

@GKopanas

1 year

Awesome recap from @PeterHedman3 on his work and the most recent progress on NeRFs.

I3D Symposium

@I3DCONF

1 year

You can now watch the talk Peter Hedman gave on the first day of I3D this year: Scaling NeRF Up and Down: Big Scenes and Real-Time View Synthesis #I3D2023

0

11

34

0

5

George Kopanas

@GKopanas

2 years

@JulienPhilip2 I would never expect such cool results from single image relighting! Genuinely impressed!

0

4

George Kopanas

@GKopanas

3 years

We are really proud to present at @EGSympRendering our Neural Rendering paper. This was a joint effort and I would like to praise my collaborators for all the great work. Watch us today at: Project Webpage:

0

6

4

George Kopanas

@GKopanas

7 months

@JonathonLuiten @jon_barron @s1ddok Dropping this here for the curious

Perspective accurate splatting | Proceedings of Graphics Interface 2004

dl.acm.org

1

0

4

George Kopanas

@GKopanas

2 months

@jon_barron @DrZeeshanZia What about advertisment? Companies pay a lot of money for 20sec videos that most of them is very close to stock footage!

1

0

3

George Kopanas

@GKopanas

8 months

@RobMakesMeta Yes definitely it will!

0

4

George Kopanas

@GKopanas

10 months

See you in LA for more fruitful and interesting discussions. I am super curious on what kind of extensions and improvements people will come up with.

1

0

4

George Kopanas

@GKopanas

3 years

@keenanisalive @dJourdan_ The discussion around these papers - including our work - is very interesting. To summarize my insight for nerf vs points: the latter can give you fast and sharp results but comparing to volumetric they can't come up with geometry in arbitrary places if not initialized properly.

0

4

George Kopanas

@GKopanas

8 months

@jon_barron @nobbis That's really not the best depth map you can get. I think this is a hard depth extraction. The expected ray termination should look much better.

1

0

4

George Kopanas

@GKopanas

1 year

@docmilanfar @jon_barron @siggraph Wow! I remember reading the SIGGRAPH paper right in the beginning of my PhD, but then forgot about it and never made the connection. It might has influenced me unconsciously 🤗 I think is a nice connection to our work. Thanks for bringing this up.

1

0

4

George Kopanas

@GKopanas

7 months

@PascalMassimino 🥹 Let me tag my partner in crime for this @Snosixtytwo

0

4

George Kopanas

@GKopanas

1 year

@alexandertmai @siggraph It's not any easy question here. This is the holy grail of this research field if you ask me. Because before shading you have first disentangle materials and light from the current representation.

1

0

4

George Kopanas

@GKopanas

1 year

@AlexandreDevaux We will release the code and try to make it as easy as possible for everyone to test it. Stay tuned :D

0

3

George Kopanas

@GKopanas

10 months

@seidtgeist @Snosixtytwo yes please <3

0

3

George Kopanas

@GKopanas

6 months

@gravicle @jon_barron They are confusing the medium with the art. The fact that I can put a few words in order doesn't make me a poet. And Genie will neither make me a 3D artist

0

3

George Kopanas

@GKopanas

9 months

@docmilanfar @marcosalvi @pfau I agree there are trade offs, there is no free lunch. But I can tell you as much, that while development we didn't consider memory at all since we are spoiled from beefy GPUs. There are a few ways memory consumption could go down significantly at least on inference.

0

3

George Kopanas

@GKopanas

8 months

@Azadux It might be that you didn't capture enough images looking up, so no sky or anything constraining gaussians to float around the top

0

3

George Kopanas

@GKopanas

5 months

@PascalMassimino @DaKangz Nice! Plugging in the conic radial kernel to the training would even make the result indistinguishable (probably)!

1

0

George Kopanas

@GKopanas

8 months

@nobbis @jon_barron That looks satisfying now 😅 I don't know how you render but I am curious why it's not almost for free since it shares so many computation with color

2

0

2

George Kopanas

@GKopanas

8 months

Is anyone else unconsciously squinting at all pictures on Twitter these days or only me?

0

3

George Kopanas

@GKopanas

7 months

@Marina_Costant Well... I can't even count my reps correctly during CrossFit 🙆🙆

0

3

George Kopanas

@GKopanas

2 months

@8Infinite8 @janusch_patas Big respect for that!

1

0

3

George Kopanas

@GKopanas

7 months

@jbhuang0604 @docmilanfar @Michael_J_Black I was randomly thinking yesterday that given that papers in CV are becoming mainly posters, the fact that the majority of the talks are invited is very much against peer review. The visibility is disproportional between accepted papers and invited talks

0

1

George Kopanas

@GKopanas

8 months

@johnowhitaker @A__Diack Rightfully burned 🔥🔥! But we might have something on the oven here...

1

0

3

George Kopanas

@GKopanas

11 months

@drsrinathsridha Super annoying. On top of that, I and others have been contacted by these accounts asking me to create a hugging face demo. I can't but assume they are on their payroll.

0

1

3

George Kopanas

@GKopanas

6 months

@jongranskog Who is going to tell that to the Graphics Researchers?

2

0

3

George Kopanas

@GKopanas

1 year

@whoshooz @siggraph Hi, great question. The light and material is currently baked in the representation similar to other NeRF-type methods. So there is no way to manipulate materials and light, but it is a great and very promising research direction. Data is capture with commodity cameras.

0

2

George Kopanas

@GKopanas

8 months

@alexcarliera Love it! It's also a very useful testbed to test ideas 💡

1

0

2

George Kopanas

@GKopanas

7 months

@danielpikl That's pretty insane 🤯

0

2

George Kopanas

@GKopanas

8 months

@nobbis 👀

0

2

George Kopanas

@GKopanas

3 years

Moving GANs to 3d! Compositing a generated image from StyleGAN to a 3d scene just happened. Kudos to Thomas Leimkuehler and @GDrettakis for making this happen at this year's SIGGRAPH Asia! The code is out

0

3

2

George Kopanas

@GKopanas

1 year

@skynetislov3 @siggraph You are right, I share the same feelings on the topic. But nowadays the amount of work and materials needed for a paper release is huge. Research groups often are overwhelmed during release periods. I hope you will try our code when we manage to release it.

0

2

George Kopanas

@GKopanas

1 year

@makeshifted @siggraph That is a very interesting article, @iquilezles did it again. But in the scale of our work, rasterizing the ellipsoids is not the bottleneck, but rather the alpha blending. Maybe @Snosixtytwo has some input here...

1

0

2

George Kopanas

@GKopanas

8 months

@aman_gif @benito_link The quality is pretty nuts for not doing any cool tricks. Wondering how it compares against a standard nerf instead of 3DGS. Hell, even add some Score destillation loss

2

0

2

George Kopanas

@GKopanas

7 months

@LumaLabsAI @Snosixtytwo Incredible implementation. Keep up the amazing work, productizing research in incredible pace.

0

2

George Kopanas

@GKopanas

10 months

@taiyasaki @Snosixtytwo @siggraph Also the code is being prepared and will be out very very soon 😁

0

2