Skip to content

Commit 1780833

Browse files
CeveloperCeveloper
committed
zdyss and bio updates
1 parent b63a09a commit 1780833

File tree

9 files changed

+71
-27
lines changed

9 files changed

+71
-27
lines changed

‎_config.yml

Lines changed: 13 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -60,24 +60,27 @@ author:
6060
name : "Cecilia Curreli"
6161
avatar : "/assets/images/profile-photo.jpg"
6262
bio : >-
63-
PhD student @ <a href="https://cvg.cit.tum.de">TUM CVG</a><br>
63+
PhD student @ <a href="https://cvg.cit.tum.de">TUM CVG</a><br> @ <a href="https://mcml.ai/">MCML</a><br>
6464
cecilia.curreli@tum.de
6565
links:
66-
- label: "CVG Page"
67-
icon: "fa-solid fa-fw fa-flask"
68-
url: "https://cvg.cit.tum.de/members/curreli"
6966
- label: "LinkedIn"
7067
icon: "fa-brands fa-fw fa-linkedin"
7168
url: "https://de.linkedin.com/in/ceciliacurreli"
7269
- label: "Google Scholar"
7370
icon: "fa-brands fa-fw fa-google-scholar"
7471
url: "https://scholar.google.com/citations?user=Y6wCaD4AAAAJ&hl=en"
72+
- label: "CVG Lab"
73+
icon: "fa-solid fa-fw fa-flask"
74+
url: "https://cvg.cit.tum.de/members/curreli"
7575
- label: "X (Twitter)"
76-
# icon: "fa-brands fa-fw fa-x-twitter"
77-
# url: "https://twitter.com/dominikmuhle"
78-
# - label: "GitHub"
79-
# icon: "fa-brands fa-fw fa-github"
80-
# url: "https://github.com/dominikmuhle"
76+
icon: "fa-brands fa-fw fa-x-twitter"
77+
url: "https://x.com/CeciCurrl"
78+
- label: "GitHub"
79+
icon: "fa-brands fa-fw fa-github"
80+
url: "https://github.com/Ceveloper"
81+
- label: "Bluesky"
82+
icon: "fa-brands fa-fw fa-bluesky"
83+
url: "https://bsky.app/profile/ceciliacurreli.bsky.social"
8184

8285
# ==================================================== COLLECTIONS ====================================================
8386
collections:
@@ -91,5 +94,5 @@ defaults:
9194
type: posts
9295
values:
9396
layout: single
94-
author_profile: false
97+
# author_profile: true
9598
# permalink: /:name/

‎_layouts/welcome.html

Lines changed: 5 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -6,15 +6,12 @@
66
{{ content }}
77

88
<p align="justify">
9-
I am pursuing my PhD with Prof. Cremers at the <a href="https://cvg.cit.tum.de">Computer Vision Group</a> of the Technical University of Munich (TUM) - Check out the awesome work of our <a href="https://cvg.cit.tum.de/publications">group</a>!
9+
I am pursuing my PhD at the Technical University of Munich with Prof. Cremers - Check out the awesome work of the <a href="https://cvg.cit.tum.de/publications">Computer Vision Group</a>!
10+
I am a junior member of the <a href="https://mcml.ai/">Munich Center of Machine Learning</a>, one of six national AI Competence Centers in Germany.
1011
<br>
11-
My <a href="publications">current research</a> focuses on generative AI, in particular diffusion for 4D computer vision tasks and 3D human motion prediction and generation.
12-
<br>
13-
In 2022 I joined <a href="https://www.satoh-lab.nii.ac.jp/">Satoh's Lab</a> at the University of Tokyo (UTokyo) and National Intitute of Informatics in Tokyo (NII) as a research intern investigating probabilistic aspects and uncertainty in conditioned human motion generation under the guidance of <a href="https://research.nii.ac.jp/~satoh/index.html">Prof. Shin'ichi Satoh</a> and <a href="https://agirbau.github.io/">Dr. Andreu Girbau</a>.
14-
<br>
15-
I completed my Master's thesis with <a href="https://www.niessnerlab.org/members/matthias_niessner/profile.html">Prof. Nießner</a> at Nießner Lab on "Probabilistic Human Motion Prediction with Scene Understanding and Occlusion Handling" completing my degree in computer science (Robotics, Cognition, Intelligence) at TU Munich.
16-
<br>
17-
I obtained my Bachelor's degree in engineering science at TU Munich after completing a thesis on "Image Retrieval Under Challenging Weather and Lighting Conditions for Place Localization in Autonomous Driving" with <a href="https://research.nvidia.com/labs/dvl/author/laura-leal-taixe/">Prof. Leal Taixè </a> and <a href="https://scholar.google.com/citations?user=d5DqmRoAAAAJ">Qunjie Zhou</a>.
12+
My <a href="publications">research</a> focuses on generative AI, in particular diffusion for 4D computer vision and 3D human motion prediction and generation.
13+
In 2022 I joined <a href="https://www.satoh-lab.nii.ac.jp/">Satoh's Lab</a> at the University of Tokyo and National Intitute of Informatics in Tokyo as a research intern under the guidance of Prof. Shin'ichi Satoh and Dr. Andreu Girbau.
14+
I completed my Master's thesis with Prof. Nießner and my my Bachelor's degree with Prof. Leal Taixè and Qunjie Zhou, both at TUM.
1815
</p>
1916

2017
<div class="hr">

‎_publications/skeletondiffusion/content.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
<div class="hero-body">
1616
<div class="container">
1717
<div class="columns is-centered has-text-centered">
18-
<div class="column is-four-fifths">
18+
<div class="column is-five-fifths">
1919
<p class="content has-text-justified">
2020
<img width="100%" src="./assets/teaser_image.png" />
2121
<br><br>

‎_publications/skeletondiffusion/index.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -24,9 +24,9 @@ authors:
2424
affiliations: "1,2"
2525
affiliations:
2626
- name: tum
27-
length: short
27+
length: long
2828
- name: mcml
29-
length: short
29+
length: long
3030

3131

3232
description: "SkeletonDiffusion is a novel nonisotropic diffusion approach for 3D Human Motion Prediction, and the first computer vision method to show that nonisotropic diffusion leads to unequivocally better performance without computational drawbacks for a structured task. We generate diverse and realistic motions achieving state-of-the-art performance on the Human3.6M and AMASS datasets."
@@ -46,7 +46,7 @@ links:
4646

4747
citation: '@inproceedings{curreli2025nonisotropic,
4848
title={Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction},
49-
author={Curreli, Cecilia and Muhle, Dominik and Saroha, Abhishek and Ye, Zhenzhang and Marin, Riccardo and Cremers, Daniel},
49+
author={Cecilia Curreli and Dominik Muhle and Abhishek Saroha and Zhenzhang Ye and Riccardo Marin and Daniel Cremers},
5050
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
5151
year={2025}
5252
}'

‎_publications/zdyss/assets/cropped.png

4.36 MB
Loading

‎_publications/zdyss/assets/teaser.png

8.73 MB
Loading

‎_publications/zdyss/assets/teaser_zdyss.png

3.65 MB
Loading

‎_publications/zdyss/content.html

Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,44 @@
1+
<!-- <section class="hero teaser">
2+
<div class="container is-max-desktop">
3+
<div class="hero-body">
4+
<video width="100%" autoplay muted loop>
5+
<source src="./assets/header_vid.mp4" type="video/mp4">
6+
Your browser does not support the video tag.
7+
</video>
8+
<p class="content has-text-justified">
9+
<i><b> Visual Odometry on KITTI. </b> Input image (top left), color-coded dense covariances (bottom left) and resulting trajectory (right). Color coding of the covariances is given by hue (size), orientation (color), and saturation (anisotropy). First sequence uses our supervised covariances, second sequence uses our unsupervised covariances.</i>
10+
</p>
11+
</div>
12+
</div>
13+
</section> -->
14+
<section class="hero is-small">
15+
<div class="hero-body">
16+
<div class="container">
17+
<div class="columns is-centered has-text-centered">
18+
<div class="column is-five-fifths">
19+
<p class="content has-text-justified">
20+
<img width="140%" src="./assets/teaser.png" />
21+
<br><br>
22+
<!-- a) We propose a symetric extension of the <a href="https://arxiv.org/abs/2204.02256" target="_blank">Probabiltistic Normal Epipolar Constraint</a>() (PNEC) to more accurately model the geometry of relative pose estimation with uncertain feature positions.
23+
<br>
24+
b) We propose a learning strategy to minimize the relative pose error by learning feature position uncertainty through differentiable nonlinear least squares (DNLS). This learning strategy can be combined with any feature extraction algorithm. We evaluate our learning framework with synthetic experiments and on real-world data in a visual odometry setting. We show that our framework is able to generalize to different feature extraction algorithms such as SuperPoint and feature tracking approaches. -->
25+
</p>
26+
</div>
27+
</div>
28+
</div>
29+
</div>
30+
</section>
31+
32+
<section class="hero is-small">
33+
<div class="hero-body">
34+
<div class="container">
35+
<div class="columns is-centered has-text-centered">
36+
<div class="column is-four-fifths">
37+
<h2 class="title is-2">Coming Soon</h2>
38+
<p class="content has-text-justified">
39+
</p>
40+
</div>
41+
</div>
42+
</div>
43+
</div>
44+
</section>

‎_publications/zdyss/index.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ layout: publications
33
permalink: /publications/zdyss/
44
# external_link: https://abhi-rf.github.io/publications/gss/
55
date: 2024_04_11 # determines sorting just take the date of the first publication as YYYY_MM_DD
6-
# image: /assets/qualitative.gif
6+
image: /assets/teaser_zdyss.png
77
# image_mouseover: assets/knowledge_distillation.png
88

99
title: "ZDySS – Zero-Shot Dynamic Scene Stylization using Gaussian Splatting"
@@ -35,8 +35,8 @@ description: "We introduce ZDySS, a zero-shot stylization framework for dynamic
3535

3636

3737
links:
38-
# - name: Project Page
39-
# link: https://keonhee-han.github.io/publications/kdbts/
38+
- name: Project Page
39+
link: /publications/zdyss/
4040
- name: Paper
4141
link: https://arxiv.org/abs/2501.03875
4242
style: "bi bi-file-earmark-richtext"
@@ -58,5 +58,5 @@ citation: '@article{saroha2025zdysszeroshotdynamic,
5858

5959

6060
# acknowledgements: 'This work was supported by the ERC Advanced Grant SIMULACRON, by the Munich Center for Machine Learning, and by the German Federal Ministry of Transport and Digital Infrastructure (BMDV) under grant 19F2251F for the ADAM project.'
61-
62-
---
61+
---
62+
{% include_relative content.html %}

0 commit comments

Comments
 (0)