Jiapeng Tang
@jiapeng_tang
Followers
1K
Following
153
Statuses
95
Ph.D. student at the Visual Computing Group @TU_Muenchen, working on 3D Computer Vision.
Munich, Bavaria
Joined November 2021
Happy to share our latest work of head Gaussian reconstruction from monocular videos via multi-view diffusion priors.
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 smartphones. Key idea: distill reconstruction constraints from a multi-view head diffusion model to complete unobserved regions. Great work by @jiapeng_tang @davidedavoli @TobiasKirschst1 @liamschoneveld
1
4
38
RT @rmbrualla: After 8 wonderful years at Google, I decided to leave Google and try something new! Working at Google was a dream come truโฆ
0
4
0
RT @MattNiessner: ๐ข๐ข ๐๐ซ๐๐๐ข๐ญ๐จ๐ซ๐๐: ๐
๐๐ฌ๐ญ ๐๐ง๐ ๐๐ซ๐๐๐ข๐ฌ๐ ๐๐ ๐๐ก๐๐ฉ๐ ๐๐๐ข๐ญ๐ข๐ง๐ ๐ข๐ข We propose a training-free 3D shape editing approach that rapidly anโฆ
0
45
0
RT @angelaqdai: ๐ขDNF: Generating 4D animations with dictionary-based neural fields! @xinyi092298 presents a new dictionary-based neural fiโฆ
0
44
0
RT @MattNiessner: ๐ข๐ข ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง๐๐ฉ๐๐๐๐ก: Audio-Driven Gaussian Avatars ๐ข๐ข We synthesize photorealistic and 3D-consistent talking human head avโฆ
0
37
0
RT @MattNiessner: Presenting super exciting 3DGS, Avatars & Diffusion papers @SIGGRAPHAsia: L3DG: Latent 3D Gaussian Diffusion https://t.cโฆ
0
30
0
nice work of dynamic 3D reconstruction with multiview video diffusion priors !
๐ Introducing CAT4D! ๐ CAT4D transforms any real or generated video into dynamic 3D scenes with a multi-view video diffusion model. The outputs are dynamic 3D models that we can freeze and look at from novel viewpoints, in real-time! Be sure to try our interactive viewer!
0
0
9
RT @MattNiessner: Want to work on cutting-edge research in #AI? We have several ๐๐ก๐ & ๐๐จ๐ฌ๐ญ๐๐จ๐ ๐จ๐ฉ๐๐ง๐ข๐ง๐ ๐ฌ in our Visual Computing & AI Lab inโฆ
0
73
0
RT @MattNiessner: ๐ข๐๐๐๐: ๐๐๐ญ๐๐ง๐ญ ๐๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ข๐๐๐ฎ๐ฌ๐ข๐จ๐ง๐ข #SIGGRAPHAsia We propose a generative diffusion model for 3D Gaussians. Key is a leโฆ
0
58
0
RT @MattNiessner: (1/3) ๐ข๐ข๐๐๐๐๐๐ ๐
๐๐ฌ๐ญ ๐๐ง๐ ๐๐๐ง๐๐ซ๐๐ฅ๐ข๐ณ๐๐๐ฅ๐ ๐๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐๐๐๐ฌ๐ข๐ข #SiggraphAsia'24 We generate photo-realistic 3D heads and renโฆ
0
56
0
RT @MattNiessner: (1/2) ๐ข๐๐๐๐: ๐๐๐ฎ๐ซ๐๐ฅ ๐๐๐ซ๐๐ฆ๐๐ญ๐ซ๐ข๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ฏ๐๐ญ๐๐ซ๐ฌ ๐ข #SIGGRAPHAsia We leverage a neural parametric representation to faciliโฆ
0
76
0
RT @angelaqdai: How can we generate high-fidelity, complex 3D scenes? @QTDSMQ's LT3SD decomposes 3D scenes into latent tree representationโฆ
0
78
0
RT @MattNiessner: (1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a thโฆ
0
32
0
RT @MattNiessner: #GCPR'24 and #VMV'24 will be held in Munich from September 10-13th! We have a fantastic set of keynote speakers and inviโฆ
0
21
0
RT @DaoyiGao: We will present DiffCAD today 2pm MDT at Mile High 2A. #SIGGRAPH2024 Come join our talk and chat about it!
0
5
0
RT @angelaqdai: Excited to present DiffCAD coming to #SIGGRAPH2024! @DaoyiGao introduces the first probabilistic single-view CAD retrievalโฆ
0
31
0
RT @JustusThies: Jiapeng @jiapeng_tang is presenting is 2nd #CVPR2024 paper called DiffuScene which is on indoor scene generation. Poster 9โฆ
0
4
0
We will present ๐๐จ๐ญ๐ข๐จ๐ง๐๐๐๐๐๐๐ญ๐ฌ at #CVPR2024 on Friday (21 Jun) at 10:30 a.m. in Arch 4E, Poster #92! Come by and chat about 4D motion generation & reconstruction๏ผ
(1/3) Super excited to present ๐๐จ๐ญ๐ข๐จ๐ง๐๐๐๐๐๐๐ญ๐ฌ at @CVPR24! We propose the first 4D diffusion model to generate dynamic surfaces, and leverage its prior to obtain a 4D surface reconstruction from sparse, noisy, and incomplete point clouds.
0
3
21
RT @JustusThies: Also Jiapeng's @jiapeng_tang work for facial performance capture is presented now at #CVPR2024 poster 93.
0
6
0