Andrea Tagliasacchi
@taiyasaki · Vancouver, Canada · joined 06 Apr 2012
Principal Scientist @ Wayve, Associate Professor @ SFU (research chair), Associate Professor @ UofT (status only)
17 261Followers
245Following
3 011Posts total
137KViews on collected posts
Ultimi post
Cerchiamo nuovi post…
Anybody that wants to go explore Copenhagen this afternoon after lunch?
3.7K views · 10 likes
· 0 reposts · 2 replies
Open on X →
Mission accomplished (14k)
Thanks @rmbrualla https://t.co/v68jXEbTfi
1.8K views · 12 likes
· 0 reposts · 0 replies
Open on X →
See you tomorrow at 7:10am at the Crowne Plaza lobby Ricardo & co!
514 views · 0 likes
· 0 reposts · 0 replies
Open on X →
@taiyasaki I was about to head out! Sent a DM!
459 views · 1 likes
· 0 reposts · 0 replies
Open on X →
Hey #ECCV2026 anybody wants to go for a 10-15Km run at the park near Orestad tomorrow morning? 🤗
6.7K views · 12 likes
· 0 reposts · 4 replies
Open on X →
@Zoom it’s been 5 years since Covid… and an intuitive way to setup “plenary talk mode” is still not there (yes yes, option is there, and yet hosts don’t know how to use it)
Tired of watching talks with zoom💩💩 occluding slides!!!! https://t.co/JojsRo4r3V
2K views · 16 likes
· 2 reposts · 1 replies
Open on X →
What’s the point of the “Cvent Events” for #ECCV26 app if none of the workshop homepages and/or descriptions are up to date? 🤬🤬
4.3K views · 37 likes
· 1 reposts · 4 replies
Open on X →
Fantastic job duo-led by my PhD students Shrisudhan Govindarajan (@Shrisudhan001) and Daniel Rebain, both co-advised with @kwangmoo_yi, and collaborators @dorverbin and @prabhubility99 https://t.co/m7ixr4UUoj
2.1K views · 35 likes
· 1 reposts · 1 replies
Open on X →
And to conclude, this is the first model that hits the four requirements @jon_barron listed in diagram **simultaneously**
No choices to make.
One model to rule them all. https://t.co/VKZ9HdwEdV
4.2K views · 53 likes
· 4 reposts · 4 replies
Open on X →
The bounding spheres of each power cell are perfect for tile-based rasterization — exactly like 3DGS, but pop-free!!
Switch a flag, and the same cells are ray traced a-la Radiant Foam in amortized constant time per step.
No BVH.
No re-training.
No quality drop. https://t.co/suS
2.7K views · 14 likes
· 3 reposts · 1 replies
Open on X →
0:04
And because power cells form a true volumetric partition, depth-ordering is provably correct for *any* ray through the camera center.
Result: ZERO popping artifacts – by construction. https://t.co/bCTLlfOgEk
2.3K views · 19 likes
· 1 reposts · 1 replies
Open on X →
0:04
But why bounded power cells matter?
1) Cells stay surface-oriented, so we do not waste capacity on empty space
2) Their bounding spheres give natural primitives for tile-based rasterization
3) And we avoid building a full Delaunay triangulation during training https://t.co/sJHlG
3.4K views · 21 likes
· 1 reposts · 1 replies
Open on X →
0:10
The recipe is Voronoi at every scale:
- Bounded *power* diagram → 3D geometry (cells with controllable extent)
- 2D Voronoi on each cell → texture / displacement
- Spherical Voronoi on each texture site → directional radiance
Three Voronoi... one differentiable representation ht
4.7K views · 44 likes
· 3 reposts · 2 replies
Open on X →
0:06
📢📢📢introducing 𝐏𝐨𝐰𝐞𝐫 𝐅𝐨𝐚𝐦
A 3D representation that can be ray traced or rasterized in real time, with NO COMPROMISE in quality.
- Project: https://t.co/LkmVQjkIt2
- arXiv: https://t.co/TtMbyKrvrp
Rasterized at 3DGS-class FPS
Ray traced at Radiant Foam speeds https://t.co/nem1I
97.1K views · 750 likes
· 111 reposts · 17 replies
Open on X →
0:10
Rispetto ad account della stessa dimensione
7 post degli ultimi 90 giorni, accanto alla fascia di 10K–100K follower. arriva a molti, ma pochi di loro reagiscono.
Visualizzazioni mediane2 022questo account924mediana per 10K–100K
Copertura, %11.71%questo account3.62%mediana per 10K–100K
Interazione, %0.33%questo account1.52%mediana per 10K–100K
| Metrica | Questo account | Mediana per 10K–100K | Rapporto |
|---|---|---|---|
| Visualizzazioni mediane per post | 2 022 | 924 | 2.19× |
| Copertura (visualizzazioni ÷ follower) | 11.71% | 3.62% | 3.24× |
| Tasso di interazione | 0.33% | 1.52% | 0.22× |
Altri account di questa fascia → Confronta con un altro account → Come sono costruiti questi parametri →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
4.7K29 Apr
3.4K
2.3K
2.7K
4.2K
2.1K
1.1K
4.3K8 Sep
2K
6.7K10 Sep
459
514
1.8K11 Sep
3.7K12 Sep
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
1.04%29 Apr
0.68%
0.91%
0.67%
1.45%
1.77%
0.38%
1.00%8 Sep
0.94%
0.25%10 Sep
0.22%
0.00%
0.73%11 Sep
0.33%12 Sep
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.
What the audience does
Likes55.8%1 027 in total
Reposts6.9%127 in total
Replies2.1%39 in total
Quotes0.8%15 in total
Bookmarks34.3%631 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Account simili
The Godmother 🇿🇦
@GodmotherThe
34.5K followers
· 340.5K posts
kwantxbt ✓
@kwantxbt
34.5K followers
· 113.8K posts
Lucky Charms
@LuckyCharms
34.5K followers
· 10.8K posts
Juice🧃 ✓
@JuiceMan3x
34.5K followers
· 23.9K posts
GOOD AMERICAN
@goodamerican
34.5K followers
· 6.9K posts
@_AmaraL577
@_AmaraL577
34.5K followers
· 119.2K posts
औरंगज़ेब 2.0 🇮🇳 ✓
@__phoenix_fire_
34.5K followers
· 120.6K posts
Mich | 🄲🄱🄶 🫡 ✓
@Mich_CBalanceG
34.5K followers
· 20.9K posts