See how easy it is to adjust features and blend shapes. Big thanks to #MakeHuman community and
@who.int data
Try the Anny demo ➡️ tinyurl.com/yt4wxsrx

Meet Anny. One model. Every body. A new human model that fits everyone!
✅ Works for all ages
✅ Free & open (Apache 2.0)
✅ Privacy-friendly (no scans)
✅ Simple parameters
Blog: tinyurl.com/5fsekm9z
Code: github.com/naver/anny
An alternative 4 #VR, #AR #Robotics.
#3DHumanModeling #OpenSource

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

Also on Tue is LUDVIG
TLDR: LUDVIG enhances Gaussian Splatting w/semantic features obtained by lifting 2D ones such as DINO/CLIP in 3D
Paper: arxiv.org/abs/2410.14462
Proj: juliettemarrie.github.io/ludvig/
@jlt-m.bsky.social @michael-arbel.bsky.social @dlarlus.bsky.social @jmairal.bsky.social 🧵8/9

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

Oct 20th is the only occasion to discover HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images @iccv.bsky.social
TLDR: HOSt3R builds upon DUSt3R for unconstrained hand-object 3D reconstruction.
Paper: arxiv.org/abs/2508.16465
Workshop HANDS: hands-workshop.org/workshop2025...
🧵4/9

Also on Oct 19th MUSt3R: Multi-view Network for Stereo 3D Reconstruction makes a guest appearance at the NeuSLAM workshop! @iccv.bsky.social
Paper: arxiv.org/abs/2503.01661
Code: github.com/naver/must3r
Workshop: sites.google.com/view/neuslam 🧵3/9

We kick off Sun Oct 19th with PANSt3R - Multi-view Consistent Panoptic Segmentation
Paper: arxiv.org/abs/2506.21348
ILR+G workshop: ilr-workshop.github.io/ICCVW2025/
OpenSUN workshop: opensun3d.github.io
TLDR: fast & scalable 3D reconstruction & scene understanding with object instances
🧵2/9

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🧵

Announcing 2 new members of the *St3R family for human-centric 3D vision tasks!
Meet HAMst3R & HOSt3R
@iccv.bsky.social
- HAMSt3R (Human-Aware Multi-view Stereo 3D Reconstruction) extends MASt3R to handle scenes involving people.
Paper: arxiv.org/abs/2508.16433
1/2 🧵

Introducing the latest model in our *St3R family! In a single step PanSt3R performs fast & scalable 3D reconstruction & scene understanding with object instances.
Paper: arxiv.org/abs/2506.21348
More info on our 3D FMs: tinyurl.com/vxw4mn9x
Accepted at #ICCV25 🎉