lealtaixe Profile Banner
Laura Leal-Taixe Profile
Laura Leal-Taixe

@lealtaixe

Followers
12K
Following
2K
Media
69
Statuses
519

Senior Research Manager at @NVIDIA. Prev Professor at @TU_Muenchen. Computer Vision mostly. Views are my own.

Joined June 2016
Don't wanna be here? Send us removal request.
@dlbcnai
Deep Learning Barcelona Symposium
3 months
Laura Leal-Taixé (@lealtaixe ) is a Senior Research Manager at @NVIDIAAI . Interview in Catalan with @neurofregides at #DLBCN 2024, hosted at @LaSalleBCN.
3
3
17
@huangjh_hjh
Jiahui Huang
3 months
[1/N] 🎥 We've made available a powerful spatial AI tool named ViPE: Video Pose Engine, to recover camera motion, intrinsics, and dense metric depth from casual videos! Running at 3–5 FPS, ViPE handles cinematic shots, dashcams, and even 360° panoramas. 🔗 https://t.co/1mGDxwgYJt
13
105
452
@aycatakmaz
Ayça Takmaz
4 months
Can we learn to complete anything in Lidar without any manual supervision? Excited to share our #ICML2025 paper “Towards Learning to Complete Anything in Lidar” from my time at @nvidia with @CristianoSalto @NeeharPeri @meinhardt_tim @RdeLutio @AljosaOsep @lealtaixe! Thread🧵👇
1
12
60
@_shumash
Masha Shugrina
5 months
Curious about 3D Gaussians, simulation, rendering and the latest from #NVIDIA? Come to the NVIDIA Kaolin Library live-coding session at #CVPR2025, powered by a cloud GPU reserved especially for you. Wed, Jun 11, 8-noon. Bring your laptop! https://t.co/joCH5DDrNk
1
20
46
@GuillemBraso
Guillem Brasó
6 months
Excited to share what we've been working on! SeNaTra introduces a backbone where segmentation emerges natively by replacing standard downsampling with grouping layers. Opens the door for a new family of zero-shot segmentation-centric backbone architectures! 🚀 Code coming soon!
@lealtaixe
Laura Leal-Taixe
6 months
The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it works 🧵 https://t.co/2I9nuLBsSz
2
15
98
@AljosaOsep
Aljosa
6 months
Turns out that if you learn to downsample (rather than using uniform grid pooling) in Vision Transformers, you no longer need dedicated upsampling layers and segmentation heads—dense image segmentation emerges natively.
Tweet card summary image
arxiv.org
Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping...
@lealtaixe
Laura Leal-Taixe
6 months
The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it works 🧵 https://t.co/2I9nuLBsSz
0
9
77
@lealtaixe
Laura Leal-Taixe
6 months
Fantastic work with the talented @GuillemBraso and @AljosaOsep. @NVIDIAAI #NVIDIAResearch
0
0
8
@lealtaixe
Laura Leal-Taixe
6 months
Coolest results on zero-shot, text-supervised semantic segmentation as well as a new kid in town for supervised semantic segmentation: the native segmentation network, the first encoder-only model capable of competing with Mask2former and the other big ones.
1
0
9
@lealtaixe
Laura Leal-Taixe
6 months
The coolest thing is that segmentation emerges even from Imagenet pre-training!
1
1
11
@lealtaixe
Laura Leal-Taixe
6 months
The secret sauce is a learned spatial grouping layer, which computes soft token assignments. The cool thing is that this enables principled feature upsampling, from masks to pixels in the encoder itself! No more heavy decoders needed!
1
1
14
@lealtaixe
Laura Leal-Taixe
6 months
Our work shows that segmentation can be inherently encoded in a model’s internal representations rather than delegated to specialized decoder modules, opening new directions in segmentation-centric backbone architectures.
1
2
9
@zhenjun_zhao
Zhenjun Zhao
7 months
A Guide to Structureless Visual Localization Vojtech Panek, Qunjie Zhou, Yaqing Ding, Sérgio Agostinho, @ZKukelova, @SattlerTorsten, @lealtaixe tl;dr: structureless localization review https://t.co/6KrUYu1iBk
1
15
57
@_akhaliq
AK
7 months
Nvidia just announced Towards Learning to Complete Anything in Lidar
9
55
413
@aycatakmaz
Ayça Takmaz
7 months
Thanks @_akhaliq for sharing! During my internship at @NVIDIAAI, we explored zero-shot panoptic completion of Lidar scans — together with @CristianoSalto @NeeharPeri @meinhardt_tim @RdeLutio @lealtaixe @AljosaOsep!
@_akhaliq
AK
7 months
Nvidia just announced Towards Learning to Complete Anything in Lidar
2
12
72
@NVIDIAAIDev
NVIDIA AI Developer
8 months
Spatial AI is increasingly important, and the newest papers from #NVIDIAResearch, 3DGRT and 3DGUT, represent significant advancements in enabling researchers and developers to explore and innovate with 3D Gaussian Splatting techniques. 💎 3DGRT (Gaussian Ray Tracing) ➡️
2
49
224
@zhenjun_zhao
Zhenjun Zhao
10 months
MATCHA:Towards Matching Anything @FeiXue94, @s_elflein, @lealtaixe, @QunjieZhou tl;dr: diffusion model->semantic+geometric features->transformer-based fusion->enhanced diffusion features->w/ DINOv2->unified feature->geometric/semantic/temporal matching https://t.co/WWjr9QEyjD
1
29
126
@JennySeidensch1
JennySeidenschwarz
10 months
If you want to try out our 3DV paper #DynOMo for dynamic, online, monocular reconstruction-based point tracking, you can do so now ☺️💃 @lealtaixe @QunjieZhou @BDuisterhof @RamananDeva https://t.co/La0rfaEdDj
2
4
28
@lealtaixe
Laura Leal-Taixe
1 year
To appear at 3DV! Congrats to the team, especially @JennySeidensch1 !
@JennySeidensch1
JennySeidenschwarz
1 year
You wondered how point tracks generated from dynamic, online, monocular reconstruction look in action? Enjoy the sneak peak of #DynOMo on TAPVID-Davis, PanopticSports and the iPhone dataset! More visuals soon 🚀@lealtaixe @QunjieZhou @BDuisterhof @RamananDeva
0
2
59