Shivangi
@shivangi2201
Followers
872
Following
2K
Media
4
Statuses
186
PhD Student, Visual Computing & AI Lab, TUM (w/ Prof. Matthias Niessner)
Munich, Bavaria
Joined September 2015
Happy to share that my internship project at DisneyResearch has been accepted to #SIGGRAPH2025. Will be presenting it in person next week. Come drop by :)
ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based
0
5
64
Happening today #SIGGRAPH2025 !! When: Wednesday, 13 August 11:45am Where: West Building, Rooms 220-222
ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based
0
1
6
๐ข LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans๐ โจ -> converts RGB-D scans into compact, realistic, and interactive 3D scenes โ featuring high-quality meshes, PBR materials, and articulated objects. ๐ท https://t.co/w8hixxH0m2 ๐ https://t.co/e7gbHJAPMD
5
66
320
Happy to share that GaussianSpeech has been accepted to #ICCV2025 !!!!
๐ข๐ข ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง๐๐ฉ๐๐๐๐ก: Audio-Driven Gaussian Avatars ๐ข๐ข We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an
1
5
60
Seven papers accepted at #ICCV2025! Exciting topics: lots of generative AI using transformers, diffusion, 3DGS, etc. focusing on image synthesis, geometry generation, avatars, and much more - check it out! So proud of everyone involved - let's go๐๐๐ https://t.co/Rd4vDGiG5p
3
30
200
Check out our #ICCV2025 work on functional 3d scan editing, learning to optimize, multi-level 3d captioning, interactive mesh editing, audio-driven avatars, & shape matching! Congrats @ElBoudjogh24002, @liuyuehcheng, @chandan__yes, @hcxrli, @shivangi2201, Emery for amazing work!
2
26
122
๐ข๐ข๐๐๐ ๐๐๐๐: ๐๐ฎ๐ฉ๐๐ซ ๐๐ฑ๐๐ข๐ญ๐๐ ๐ญ๐จ ๐๐ง๐ง๐จ๐ฎ๐ง๐๐ ๐๐ฉ๐๐๐ญ๐ข๐๐ฅ ๐๐ ๐ข๐ข Weโre building Spatial Foundation Models โ a new paradigm of generative AI that reasons about space and time! Really stoked about our world-class team โ itโs gonna be mind-boggling!
๐๐๐Announcing our $13M funding round to build the next generation of AI: ๐๐ฉ๐๐ญ๐ข๐๐ฅ ๐
๐จ๐ฎ๐ง๐๐๐ญ๐ข๐จ๐ง ๐๐จ๐๐๐ฅ๐ฌ that can generate entire 3D environments anchored in space & time. ๐๐๐ Interested? Join our world-class team: ๐ https://t.co/U0JNkNwp3s
#GenAI #3DAI
29
71
534
๐ขAnimating the Uncaptured ๐ข We animate 3D humanoid meshes using video diffusion priors given a text prompt. ๐ฅ https://t.co/EpFW86gaRw ๐ https://t.co/suMQs8oQCL Realistic motion generation for 3D characters - without motion capture! ๐ Great work by @marcbenedi @angelaqdai
3
40
124
๐ขMeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing๐ข Users can interactively design 3D models just from a sketch-based interface - check out the demo :) We break down the design process into addition with an autoregressive generator and
4
88
439
๐ข๐ข๐๐๐
: ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ฏ๐๐ญ๐๐ซ ๐๐๐๐จ๐ง๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ข๐จ๐ง ๐๐ซ๐จ๐ฆ ๐๐จ๐ง๐จ๐๐ฎ๐ฅ๐๐ซ ๐๐ข๐๐๐จ๐ฌ ๐ฏ๐ข๐ ๐๐ฎ๐ฅ๐ญ๐ข-๐ฏ๐ข๐๐ฐ ๐๐ข๐๐๐ฎ๐ฌ๐ข๐จ๐ง๐ข๐ข We reconstruct animatable Gaussian head avatars from monocular videos captured by commodity devices such as
2
31
125
Super happy to present our #NeurIPS paper ๐๐จ๐ก๐๐ซ๐๐ง๐ญ ๐๐ ๐๐๐๐ง๐ ๐๐ข๐๐๐ฎ๐ฌ๐ข๐จ๐ง ๐
๐ซ๐จ๐ฆ ๐ ๐๐ข๐ง๐ ๐ฅ๐ ๐๐๐ ๐๐ฆ๐๐ ๐ in Vancouver. Come to our poster #2804 on Wednesday 11am - 2pm in East Exhibit Hall A-C and say hi if you want to learn more about 3D Scene
3
38
118
(1/3) ๐ข๐ข๐๐๐๐๐๐ ๐
๐๐ฌ๐ญ ๐๐ง๐ ๐๐๐ง๐๐ซ๐๐ฅ๐ข๐ณ๐๐๐ฅ๐ ๐๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐๐๐๐ฌ๐ข๐ข #SiggraphAsia'24 We generate photo-realistic 3D heads and render them with Gaussian Splatting at 1k resolution in real-time. https://t.co/NAR7WW0rIc
https://t.co/ZlBbkptZGr
5
58
296
(1/2) How to accelerate the reconstruction of 3D Gaussian Splatting? 3DGS-LM replaces the commonly used ADAM optimizer with a tailored Levenberg-Marquardt (LM). => We are ๐๐% ๐๐๐ฌ๐ญ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐๐ for the same quality. https://t.co/F4uB4DpJGt
https://t.co/Ju0Y2VxH7z
2
53
194
Want to work on cutting-edge research in #AI? We have several ๐๐ก๐ & ๐๐จ๐ฌ๐ญ๐๐จ๐ ๐จ๐ฉ๐๐ง๐ข๐ง๐ ๐ฌ in our Visual Computing & AI Lab in Munich! Topics have a strong focus on GenAI, including 3DGs, NeRFs, Diffusion Models, LLMs, etc. Share & apply :) https://t.co/HWQhI69CZ0
7
73
355
(1/2) ๐ข๐๐๐๐: ๐๐๐ฎ๐ซ๐๐ฅ ๐๐๐ซ๐๐ฆ๐๐ญ๐ซ๐ข๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ฏ๐๐ญ๐๐ซ๐ฌ ๐ข #SIGGRAPHAsia We leverage a neural parametric representation to facilitate precise control over 3D Gaussians to obtain high-fidelity avatars. https://t.co/jbrCHv7ej1
https://t.co/ajxDCsx8jZ
9
75
381
#GCPR'24 and #VMV'24 will be held in Munich from September 10-13th! We have a fantastic set of keynote speakers and invited PI talks - check it out! https://t.co/29Z0sezykF Also the registration is open: early bird until **August 12th** - join us for an amazing event :)
0
21
57
Excited to present DiffCAD coming to #SIGGRAPH2024! @DaoyiGao introduces the first probabilistic single-view CAD retrieval & alignment. We train only on synthetic -> generalize robustly to real images! Check out the code: https://t.co/hBCoN0Hx3w w/@david_roz_, @StefanLeuteneg1
0
31
116
FaceTalk will be presented at #CVPR2024 during Friday's poster session (21 June). Location๏ผArch 4A-E Time๏ผ10:30-12:00 Come drop by if you're interested in audio-driven facial animation.
(1/2) Check out "FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models"! We synthesize high-fidelity motion sequences of neural parametric head models from audio input. Works with music and various languages :) https://t.co/dkZsm8hD5U
https://t.co/PJ2np50fyz
1
10
50
Delighted to share the #CVPR 2024 paper compilation of our TUM Visual Computing Lab & collaborators: https://t.co/P8dHKDWpba Amazing work by everyone - so proud about it. It's going to be a fantastic conference in #Seattle this week. Looking forward to seeing everyone!
1
21
115