Lei Li
@craigleili
Followers
239
Following
90
Statuses
66
Postdoc @ 3D AI Lab, Technical University of Munich
Joined July 2010
RT @MattNiessner: Tomorrow in our TUM AI - Lecture Series with none other than George Drettakis. He'll talk about "๐๐ก๐ ๐๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ฉ๐ฅ๐๐ญ๐ญ๐ขโฆ
0
53
0
RT @angelaqdai: ๐ข ScanNet++ v2 Benchmark Release! ๐ Test your state-of-the-art models on: ๐น Novel View Synthesis ๐ธโก๏ธ๐ผ๏ธ ๐น 3D Semantic & Insโฆ
0
42
0
RT @angelaqdai: Excited to announce ScanNet++ v2!๐ @chandan__yes and @liuyuehcheng have been working tirelessly to bring: ๐น1006 high-fidelโฆ
0
110
0
RT @TU_Muenchen: Scientists, including @angelaqdai, Professor of 3D #ArtificialIntelligence, developed DriverAerNet++, the largest open-souโฆ
0
12
0
๐Check out our latest work MeshArt led by @DaoyiGao MeshArt generates articulated 3D objects with clean, compact geometry that can animated at different articulation states! A step forward in understanding object functionality and interactions๐
๐ขMeshArt: Generating Articulated Meshes with Structure-guided Transformers @DaoyiGao generates articulated meshes with a hierarchical transformer, modeling articulation-aware structures that guide mesh synthesis. w/ @yawarnihal @craigleili Project:
0
3
11
RT @MattNiessner: ๐ข๐ข๐๐๐
: ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ฏ๐๐ญ๐๐ซ ๐๐๐๐จ๐ง๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ข๐จ๐ง ๐๐ซ๐จ๐ฆ ๐๐จ๐ง๐จ๐๐ฎ๐ฅ๐๐ซ ๐๐ข๐๐๐จ๐ฌ ๐ฏ๐ข๐ ๐๐ฎ๐ฅ๐ญ๐ข-๐ฏ๐ข๐๐ฐ ๐๐ข๐๐๐ฎ๐ฌ๐ข๐จ๐ง๐ข๐ข We reconstruct animatable Gaussiaโฆ
0
31
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 @angelaqdai: ๐ขSceneFactor: Generating & editing 3D indoor scenes from text! @ABokhovkin presents a factored latent diffusion for controโฆ
0
27
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 @angelaqdai: Excited to present DrivAerNet++, coming to #NeurIPS24 Datasets & Benchmarks! DrivAerNet++ introduces the first large-scaleโฆ
0
43
0
Souhail is presenting our work "To Supervise or Not to Supervise" at ๐Poster 35 now #ECCV2024. Drop by and say hi! ๐
Excited to share our latest #ECCV2024 paper, "To Supervise or Not to Supervise", on point cloud transfer learning. Our layerwise feature analysis leads to a geometric regularization strategy boosting supervised pre-training transferability! ๐
0
0
6
RT @YujinChen_cv: We present Mesh2NeRF at #ECCV this afternoon (Wed Oct 2, 16:30 - 18:30). Poster Session: 4 Poster Board ID: 290 Come byโฆ
0
6
0
Supervised or not?๐คThat's a key question in 3D transfer learning! Join us tomorrow morning to discuss how to improve supervised pre-training transferability with Souhail.๐#ECCV2024 ๐๏ธ Thursday, Oct 3rd, 10:30 - 12:30 ๐Poster 35
Excited to share our latest #ECCV2024 paper, "To Supervise or Not to Supervise", on point cloud transfer learning. Our layerwise feature analysis leads to a geometric regularization strategy boosting supervised pre-training transferability! ๐
0
1
2
RT @angelaqdai: So honored to receive the ECVA Young Researcher Award at @eccvconf! ๐ Very grateful for an amazing set of collaborators andโฆ
0
14
0
A fun podcast episode generated by NotebookLM discussing our #ECCV2024 work "To Supervise or Not to Supervise"๐๏ธ Give it a listen for some great insights and laughs! ๐๐
Excited to share our latest #ECCV2024 paper, "To Supervise or Not to Supervise", on point cloud transfer learning. Our layerwise feature analysis leads to a geometric regularization strategy boosting supervised pre-training transferability! ๐
1
1
7
RT @MattNiessner: (1/2) How to accelerate the reconstruction of 3D Gaussian Splatting? 3DGS-LM replaces the commonly used ADAM optimizer wโฆ
0
47
0
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: (1/2) ๐ข๐๐๐๐: ๐๐๐ฎ๐ซ๐๐ฅ ๐๐๐ซ๐๐ฆ๐๐ญ๐ซ๐ข๐ ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ฏ๐๐ญ๐๐ซ๐ฌ ๐ข #SIGGRAPHAsia We leverage a neural parametric representation to faciliโฆ
0
76
0