Vincent Leroy
@vincentleroy.bsky.social
GEODE Team Lead (Geometric Deep Learning)
3D vision researcher @NaverLabsEurope
3D vision researcher @NaverLabsEurope
Reposted by Vincent Leroy
A new model for human mesh recovery, high-performing and w/o using any 3D scans, has been published by my excellent colleagues at @naverlabseurope.bsky.social. Excellent work!
November 6, 2025 at 11:37 AM
A new model for human mesh recovery, high-performing and w/o using any 3D scans, has been published by my excellent colleagues at @naverlabseurope.bsky.social. Excellent work!
Reposted by Vincent Leroy
Nice article on PansSt3R with LojzeZust in #ICCV2025 Daily! rsipvision.com/ICCV2025-Tue...
October 22, 2025 at 8:05 AM
Nice article on PansSt3R with LojzeZust in #ICCV2025 Daily! rsipvision.com/ICCV2025-Tue...
If you want to learn more about general models for 3D and semantic understanding, or just have a quick chat, come meet us this afternoon at posters #462 (HAMSt3R) and #540 (PanSt3R) :)
October 21, 2025 at 8:08 PM
If you want to learn more about general models for 3D and semantic understanding, or just have a quick chat, come meet us this afternoon at posters #462 (HAMSt3R) and #540 (PanSt3R) :)
Reposted by Vincent Leroy
We’re #HiringNow a Senior Research Scientist in ML for Robotics in Grenoble, France
Don't miss us at #iros2025 this week to chat about the role, research & team with Darko Drakulic & @rbregier.bsky.social on Tue 21 & Thur 23 Oct!
More info on where to find them & job ad ⬇️⬇️
Don't miss us at #iros2025 this week to chat about the role, research & team with Darko Drakulic & @rbregier.bsky.social on Tue 21 & Thur 23 Oct!
More info on where to find them & job ad ⬇️⬇️
October 20, 2025 at 2:05 PM
We’re #HiringNow a Senior Research Scientist in ML for Robotics in Grenoble, France
Don't miss us at #iros2025 this week to chat about the role, research & team with Darko Drakulic & @rbregier.bsky.social on Tue 21 & Thur 23 Oct!
More info on where to find them & job ad ⬇️⬇️
Don't miss us at #iros2025 this week to chat about the role, research & team with Darko Drakulic & @rbregier.bsky.social on Tue 21 & Thur 23 Oct!
More info on where to find them & job ad ⬇️⬇️
Reposted by Vincent Leroy
We round off #iccv25 with highlight paper Geo4D on Thur
TLDR: Geo4D repurposes a video diffusion model to reconstruct dynamic scenes in 4D
Paper: arxiv.org/abs/2504.07961
Project: geo4d.github.io
@chuanxiaz.bsky.social @dlarlus.bsky.social rlus.bsky.social @oxford-vgg.bsky.social gg.bsky.social
🧵9
TLDR: Geo4D repurposes a video diffusion model to reconstruct dynamic scenes in 4D
Paper: arxiv.org/abs/2504.07961
Project: geo4d.github.io
@chuanxiaz.bsky.social @dlarlus.bsky.social rlus.bsky.social @oxford-vgg.bsky.social gg.bsky.social
🧵9
October 18, 2025 at 6:56 AM
We round off #iccv25 with highlight paper Geo4D on Thur
TLDR: Geo4D repurposes a video diffusion model to reconstruct dynamic scenes in 4D
Paper: arxiv.org/abs/2504.07961
Project: geo4d.github.io
@chuanxiaz.bsky.social @dlarlus.bsky.social rlus.bsky.social @oxford-vgg.bsky.social gg.bsky.social
🧵9
TLDR: Geo4D repurposes a video diffusion model to reconstruct dynamic scenes in 4D
Paper: arxiv.org/abs/2504.07961
Project: geo4d.github.io
@chuanxiaz.bsky.social @dlarlus.bsky.social rlus.bsky.social @oxford-vgg.bsky.social gg.bsky.social
🧵9
Reposted by Vincent Leroy
Tuesday is Poster Session 2 with
HAMS3tR: Human-Aware Multi-view Stereo 3D Reconstruction @iccv.bsky.social
TLDR: HAMSt3R extends MASt3R to handle scenes involving people.
Paper: arxiv.org/abs/2508.16433
@weinzaepfelp.bsky.social @vincentleroy.bsky.social 🧵7/9
HAMS3tR: Human-Aware Multi-view Stereo 3D Reconstruction @iccv.bsky.social
TLDR: HAMSt3R extends MASt3R to handle scenes involving people.
Paper: arxiv.org/abs/2508.16433
@weinzaepfelp.bsky.social @vincentleroy.bsky.social 🧵7/9
October 18, 2025 at 6:56 AM
Tuesday is Poster Session 2 with
HAMS3tR: Human-Aware Multi-view Stereo 3D Reconstruction @iccv.bsky.social
TLDR: HAMSt3R extends MASt3R to handle scenes involving people.
Paper: arxiv.org/abs/2508.16433
@weinzaepfelp.bsky.social @vincentleroy.bsky.social 🧵7/9
HAMS3tR: Human-Aware Multi-view Stereo 3D Reconstruction @iccv.bsky.social
TLDR: HAMSt3R extends MASt3R to handle scenes involving people.
Paper: arxiv.org/abs/2508.16433
@weinzaepfelp.bsky.social @vincentleroy.bsky.social 🧵7/9
Reposted by Vincent Leroy
It's a marathon Sunday for @gabrielacsurka.bsky.social – co-author of PANst3R, Gabriela is also giving 2 invited wksp talks AND keynote dinner speech #WiCV 😅
CALIPOSE: 🏃https://sites.google.com/view/calipose2025/
CRoCoDL: 🏃♀️https://localizoo.com/workshop/
WICV: sites.google.com/view/wicv-ic... 🧵6/9
CALIPOSE: 🏃https://sites.google.com/view/calipose2025/
CRoCoDL: 🏃♀️https://localizoo.com/workshop/
WICV: sites.google.com/view/wicv-ic... 🧵6/9
October 18, 2025 at 6:56 AM
It's a marathon Sunday for @gabrielacsurka.bsky.social – co-author of PANst3R, Gabriela is also giving 2 invited wksp talks AND keynote dinner speech #WiCV 😅
CALIPOSE: 🏃https://sites.google.com/view/calipose2025/
CRoCoDL: 🏃♀️https://localizoo.com/workshop/
WICV: sites.google.com/view/wicv-ic... 🧵6/9
CALIPOSE: 🏃https://sites.google.com/view/calipose2025/
CRoCoDL: 🏃♀️https://localizoo.com/workshop/
WICV: sites.google.com/view/wicv-ic... 🧵6/9
Reposted by Vincent Leroy
If you’ve never heard the story of how the #DUSt3R or *St3R family was born & what’s going on now - don’t miss @vincentleroy.bsky.social & his new talk at the #E2E3D workshop, also Oct 19th
Workshop E2E3D (afternoon): e2e3d.github.io 🧵5/9
Workshop E2E3D (afternoon): e2e3d.github.io 🧵5/9
October 18, 2025 at 6:56 AM
If you’ve never heard the story of how the #DUSt3R or *St3R family was born & what’s going on now - don’t miss @vincentleroy.bsky.social & his new talk at the #E2E3D workshop, also Oct 19th
Workshop E2E3D (afternoon): e2e3d.github.io 🧵5/9
Workshop E2E3D (afternoon): e2e3d.github.io 🧵5/9
Reposted by Vincent Leroy
Aloha #iccv25 – here we come! Excited to be presenting new *St3R models PANSt3R, HAMSt3R & HOSt3R. We're also introducing ‘Geo4D' and ‘LUDVIG’ 🫢 giving invited talks and mentoring! Full @iccv.bsky.social
programme below (or tinyurl.com/asbn5b5d) 🧵1/9
programme below (or tinyurl.com/asbn5b5d) 🧵1/9
ICCV 2025
5 papers, invited speaker, WiCV sponsor and Challenge sponsor
tinyurl.com
October 18, 2025 at 6:56 AM
Aloha #iccv25 – here we come! Excited to be presenting new *St3R models PANSt3R, HAMSt3R & HOSt3R. We're also introducing ‘Geo4D' and ‘LUDVIG’ 🫢 giving invited talks and mentoring! Full @iccv.bsky.social
programme below (or tinyurl.com/asbn5b5d) 🧵1/9
programme below (or tinyurl.com/asbn5b5d) 🧵1/9
Reposted by Vincent Leroy
🔥 ACE-G, the next evolutionary step of ACE at #ICCV2025 🔥
We disentangle coordinate regression and latent map representation which lets us pre-train the regressor to generalize from mapping data to difficult query images.
Page: nianticspatial.github.io/ace-g/
Stellar work by Leonard Bruns et al.!
We disentangle coordinate regression and latent map representation which lets us pre-train the regressor to generalize from mapping data to difficult query images.
Page: nianticspatial.github.io/ace-g/
Stellar work by Leonard Bruns et al.!
October 14, 2025 at 8:24 AM
🔥 ACE-G, the next evolutionary step of ACE at #ICCV2025 🔥
We disentangle coordinate regression and latent map representation which lets us pre-train the regressor to generalize from mapping data to difficult query images.
Page: nianticspatial.github.io/ace-g/
Stellar work by Leonard Bruns et al.!
We disentangle coordinate regression and latent map representation which lets us pre-train the regressor to generalize from mapping data to difficult query images.
Page: nianticspatial.github.io/ace-g/
Stellar work by Leonard Bruns et al.!
Reposted by Vincent Leroy
📽️ Check out Visual Odometry Transformer! VoT is an end-to-end model for getting accurate metric camera poses from monocular videos.
vladimiryugay.github.io/vot/
vladimiryugay.github.io/vot/
October 7, 2025 at 9:02 AM
📽️ Check out Visual Odometry Transformer! VoT is an end-to-end model for getting accurate metric camera poses from monocular videos.
vladimiryugay.github.io/vot/
vladimiryugay.github.io/vot/
Reposted by Vincent Leroy
RaySt3R was accepted to NeurIPS! Check out the HuggingFace demo for image to 3D in cluttered scenes huggingface.co/spaces/bartd...
September 19, 2025 at 5:28 PM
RaySt3R was accepted to NeurIPS! Check out the HuggingFace demo for image to 3D in cluttered scenes huggingface.co/spaces/bartd...
Reposted by Vincent Leroy
Wrt to RoPE: People are applying it wrongly for multi-view, if you do it VGGT style you will mix the positions of all the images. You should do it independently (i.e. no rope between images).
September 18, 2025 at 10:07 AM
Wrt to RoPE: People are applying it wrongly for multi-view, if you do it VGGT style you will mix the positions of all the images. You should do it independently (i.e. no rope between images).
Reposted by Vincent Leroy
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Nikhil Keetha et 16 al.
tl;dr: VGGT meets Pow3R. No RoPE. Metric scale.
arxiv.org/abs/2509.13414
1/
Nikhil Keetha et 16 al.
tl;dr: VGGT meets Pow3R. No RoPE. Metric scale.
arxiv.org/abs/2509.13414
1/
September 18, 2025 at 7:15 AM
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Nikhil Keetha et 16 al.
tl;dr: VGGT meets Pow3R. No RoPE. Metric scale.
arxiv.org/abs/2509.13414
1/
Nikhil Keetha et 16 al.
tl;dr: VGGT meets Pow3R. No RoPE. Metric scale.
arxiv.org/abs/2509.13414
1/
Reposted by Vincent Leroy
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
@nikv9.bsky.social et al.
tl;dr: flexible input & metric output version of VGGT
arxiv.org/abs/2509.13414
@nikv9.bsky.social et al.
tl;dr: flexible input & metric output version of VGGT
arxiv.org/abs/2509.13414
September 18, 2025 at 10:57 AM
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
@nikv9.bsky.social et al.
tl;dr: flexible input & metric output version of VGGT
arxiv.org/abs/2509.13414
@nikv9.bsky.social et al.
tl;dr: flexible input & metric output version of VGGT
arxiv.org/abs/2509.13414
Reposted by Vincent Leroy
And here is a link to the thesis itself: liu.diva-portal.org/smash/record...
Towards the Next Generation of 3D Reconstruction
liu.diva-portal.org
September 17, 2025 at 6:31 AM
And here is a link to the thesis itself: liu.diva-portal.org/smash/record...
Reposted by Vincent Leroy
Towards the Next Generation of 3D Reconstruction
@parskatt.bsky.social PhD Thesis.
tl;dr: would be useful in teaching image matching - nice explanations. (too) Fancy and stylish notation. Cool Ack section and cover image.
liu.diva-portal.org/smash/record...
@parskatt.bsky.social PhD Thesis.
tl;dr: would be useful in teaching image matching - nice explanations. (too) Fancy and stylish notation. Cool Ack section and cover image.
liu.diva-portal.org/smash/record...
September 18, 2025 at 6:25 AM
Towards the Next Generation of 3D Reconstruction
@parskatt.bsky.social PhD Thesis.
tl;dr: would be useful in teaching image matching - nice explanations. (too) Fancy and stylish notation. Cool Ack section and cover image.
liu.diva-portal.org/smash/record...
@parskatt.bsky.social PhD Thesis.
tl;dr: would be useful in teaching image matching - nice explanations. (too) Fancy and stylish notation. Cool Ack section and cover image.
liu.diva-portal.org/smash/record...
Reposted by Vincent Leroy
How to name your method: a comprehensive flow chart
September 13, 2025 at 3:32 PM
How to name your method: a comprehensive flow chart
Reposted by Vincent Leroy
Want more visibility for your SLAM-related paper at #ICCV2025?
Submit to the Nectar Track of our Neural SLAM workshop before Sep. 15!
We welcome any recently published high-quality papers (ICCV, CVPR, NeurIPS, Arxiv, etc.)!
🌐 More info: sites.google.com/view/neuslam...
Submit to the Nectar Track of our Neural SLAM workshop before Sep. 15!
We welcome any recently published high-quality papers (ICCV, CVPR, NeurIPS, Arxiv, etc.)!
🌐 More info: sites.google.com/view/neuslam...
September 5, 2025 at 2:48 PM
Want more visibility for your SLAM-related paper at #ICCV2025?
Submit to the Nectar Track of our Neural SLAM workshop before Sep. 15!
We welcome any recently published high-quality papers (ICCV, CVPR, NeurIPS, Arxiv, etc.)!
🌐 More info: sites.google.com/view/neuslam...
Submit to the Nectar Track of our Neural SLAM workshop before Sep. 15!
We welcome any recently published high-quality papers (ICCV, CVPR, NeurIPS, Arxiv, etc.)!
🌐 More info: sites.google.com/view/neuslam...
Reposted by Vincent Leroy
Adding the fab view of Grenoble by night!
September 4, 2025 at 7:50 AM
Adding the fab view of Grenoble by night!
Reposted by Vincent Leroy
The 4th day of the #PAISS2025 summer school is opened by Jérôme Revaud presenting 'Data-driven 3d vision' and the DUSt3R and MASt3R family of models.
September 4, 2025 at 7:43 AM
The 4th day of the #PAISS2025 summer school is opened by Jérôme Revaud presenting 'Data-driven 3d vision' and the DUSt3R and MASt3R family of models.
Reposted by Vincent Leroy
We couldn't get more lucky with the weather last night for the #PAISS2025 gala - sponsored by @naverlabseurope.bsky.social
September 4, 2025 at 7:04 AM
We couldn't get more lucky with the weather last night for the #PAISS2025 gala - sponsored by @naverlabseurope.bsky.social
Reposted by Vincent Leroy
Third day of #PAISS2025 starts strong with a talk from @science4all.org about 'AI Security'
September 3, 2025 at 7:46 AM
Third day of #PAISS2025 starts strong with a talk from @science4all.org about 'AI Security'
Reposted by Vincent Leroy
1/4 🚀 We’re excited to release MVTracker (ICCV 2025 Oral), the first data-driven multi-view 3D point tracker. MVTracker tracks arbitrary 3D points across multiple cameras, handling occlusions and varied camera setups without per-sequence optimization.
August 29, 2025 at 12:38 PM
1/4 🚀 We’re excited to release MVTracker (ICCV 2025 Oral), the first data-driven multi-view 3D point tracker. MVTracker tracks arbitrary 3D points across multiple cameras, handling occlusions and varied camera setups without per-sequence optimization.
Reposted by Vincent Leroy
HOSt3R (Keypoint-free Hand-Object 3D Reconstruction from RGB images) builds upon DUSt3R for unconstrained hand-object 3D reconstruction - example 3D shape output below.
Paper: arxiv.org/abs/2508.16465
More info on @naverlabseurope.bsky.social
@iccv.bsky.social ➡️ tinyurl.com/2p9kcb86
2/2🧵
Paper: arxiv.org/abs/2508.16465
More info on @naverlabseurope.bsky.social
@iccv.bsky.social ➡️ tinyurl.com/2p9kcb86
2/2🧵
August 25, 2025 at 2:15 PM
HOSt3R (Keypoint-free Hand-Object 3D Reconstruction from RGB images) builds upon DUSt3R for unconstrained hand-object 3D reconstruction - example 3D shape output below.
Paper: arxiv.org/abs/2508.16465
More info on @naverlabseurope.bsky.social
@iccv.bsky.social ➡️ tinyurl.com/2p9kcb86
2/2🧵
Paper: arxiv.org/abs/2508.16465
More info on @naverlabseurope.bsky.social
@iccv.bsky.social ➡️ tinyurl.com/2p9kcb86
2/2🧵