Ignas Budvytis

Machine Learning and Computer Vision expert. Former Assistant Professor at the Department of Engineering, University of Cambridge

[Akash Sengupta @AkashSengupta97]

Locally controlling SMPL body shape has uses in 3D shape estimation and generation. Check out the following repo for body-part-based modification of SMPL shape. There is a lot of room for research and improvements!

Code: https://t.co/0lK0e6qmnH

[Akash Sengupta @AkashSengupta97]

Easily one of the best talks I’ve heard at #CVPR2024!

[Ignas Budvytis @IgnasBud]

@BaeGwangbin Stellar talk!

[Zhenjun Zhao @zhenjun_zhao]

NPLMV-PS: Neural Point-Light Multi-View Photometric Stereo

Fotios Logothetis, @IgnasBud, @robertocipolla

tl;dr: pixel intensity->3D shape; model point light attenuation, explicitly raytrace cast shadows and optimise a fully neural material renderer

https://t.co/4SOVNBI1Oa

[Machine Learning (ML) Papers @Memoirs]

Task Agnostic Architecture for Algorithm Induction via Implicit Composition. https://t.co/a6jyWM6TT6

[Ignas Budvytis @IgnasBud]

@BaeGwangbin Impressive work, @BaeGwangbin! Great to see robustness to orientation and scale change. Would love to see a NeRF reconstruction on this data built real time.

[feixue @FeiXue94]

I'm excited to introduce our work on efficient visual localization - PRAM: Place Recognition Anywhere Model for Efficient Visual Localization with @IgnasBud @robertocipolla
1. Self-defined 3D landmarks as in humans’ perception system - not limited to classic semantic labels

[Zhenjun Zhao @zhenjun_zhao]

PRAM: Place Recognition Anywhere Model for Efficient Visual Localization

Fei Xue, @IgnasBud, @robertocipolla

tl;dr: map-centric landmark definition; recognition->sparse self-defined landmarks->landmark-wise matching
new paradigm for visual localization?

https://t.co/npnQKt2yK2

[Ignas Budvytis @IgnasBud]

@AkashSengupta97 @GoogleAI @thiemoall @nikoskolot @enric_corona @CSminchisescu Excellent work! Great to see diffusion processes incorporated into reconstruction.

[Akash Sengupta @AkashSengupta97]

Excited to be presenting “DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans” at #CVPR2024!
Project page: https://t.co/liNINEskaC

Huge thanks to my awesome @GoogleAI internship hosts: @thiemoall, @nikoskolot, @enric_corona, Andrei Zanfir, @CSminchisescu!

1/n

[Florian Langer @FlorianLanger15]

Excited to be presenting my latest work "Sparse Multi-Object Render-and-Compare" at #BMVC2023. CAD model based 3D scene representations have exciting applications for AR and robotics.
- with @IgnasBud and @robertocipolla
https://t.co/QkPNRSCrzG

[Ignas Budvytis @IgnasBud]

@pathajali Also highly inspired by tremendous effort and ingenuity of @Sahil_J_S

[Ignas Budvytis @IgnasBud]

@pathajali Excellent work!

[feixue @FeiXue94]

very interesting work. similar idea to our CVPR2023 paper IMP: Iterative Matching and Pose Estimation with Adaptive Pooling w/ @IgnasBud @robertocipolla
https://t.co/s3dxG8DqaG
Source code including the training part is available at https://t.co/Op1zXQRtua

[Akash Sengupta @AkashSengupta97]

Can't wait to be at #CVPR in Vancouver next week! Drop in to the PM poster session on Tuesday to check out HuManiFlow - our probabilistic approach to 3D human pose and shape estimation.

Video: https://t.co/aKbiGzSi9n
More details: https://t.co/kave90A6pv

[feixue @FeiXue94]

Introducing our work 'IMP: Iterative Matching and Pose Estimation with Adaptive Pooling': efficient matching and pose estimation with transformers.
#CVPR2023
w/ @IgnasBud @robertocipolla

paper: https://t.co/Lx4hSey83A
code: https://t.co/Op1zXQRtua

[feixue @FeiXue94]

@CVPR A new approach of using sematics for long-term localization

SFD2: Semantic-guided Feature Detection and Description @feixu94 @IgnasBud @robertocipolla
https://t.co/H7MvfYHaCh
implicit semantics embedding into keypoints; no gt for training; no explicit labels at test time

[Akash Sengupta @AkashSengupta97]

Really looking forward to presenting our paper "HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation" at CVPR 2023!

w/ @IgnasBud and @robertocipolla

Paper + code: https://t.co/D34naF6hLV

1/3

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

SFD2: Semantic-guided Feature Detection and Description

Fei Xue, @IgnasBud, @robertocipolla

tl;dr: more principled approach to use segmentation for image matching, than class-name filtering.
https://t.co/NeQx2pzT7w
#CVPR2023

[Ignas Budvytis @IgnasBud]

@vijaycivs Congratulations!