Yueh-Cheng Liu Profile
Yueh-Cheng Liu

@liuyuehcheng

Followers
221
Following
67
Media
0
Statuses
35

PhD Student at @TU_Muenchen 3D AI Lab

Taiwan
Joined May 2020
Don't wanna be here? Send us removal request.
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
3 days
See you today at #ICCV2025 this afternoon 14:30-16:30 at poster 301!
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
2 months
We will present QuickSplat at #ICCV2025! ๐ŸŽ‰ Data-driven 2DGS initialization and densification makes 3D surface reconstruction fast & accurate! ๐Ÿš€ Projcet: https://t.co/SKJ7XRWTVt Arxiv:
0
3
9
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
12 days
Our new benchmark iPhone NVS. Super interesting when the data captures are not โ€œperfectโ€.
@angelaqdai
Angela Dai
@angelaqdai
13 days
๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขWe've released the ScanNet++ Novel View Synthesis Benchmark for iPhone data! ๐Ÿฅณ Test your models on RGBD video featuring real-world challenges like exposure changes & motion blur! Download the newest iPhone NVS test split and submit your results! โฌ‡๏ธ https://t.co/hLnFwifvTL
0
7
67
@MattNiessner
Matthias Niessner
@MattNiessner
1 month
Can we use video diffusion to generate 3D scenes? ๐–๐จ๐ซ๐ฅ๐๐„๐ฑ๐ฉ๐ฅ๐จ๐ซ๐ž๐ซ (#SIGGRAPHAsia25) creates fully-navigable scenes via autoregressive video generation. Text input -> 3DGS scene output & interactive rendering! ๐ŸŒ https://t.co/HBdrmU4Oqq ๐Ÿ“ฝ๏ธ https://t.co/AQr0p4uWBZ
7
74
375
@craigleili
Lei Li
@craigleili
2 months
Excited to join @uvadatascience as an Assistant Professor! Deeply grateful to my advisors @angelaqdai, Maks Ovsjanikov, Hongbo Fu, and Chiew-Lan Tai for their unwavering support. ๐Ÿ“ขWe are recruiting PhD students and postdocs to work on #SpatialAI. Flyer below with details!
5
18
136
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
2 months
We will present QuickSplat at #ICCV2025! ๐ŸŽ‰ Data-driven 2DGS initialization and densification makes 3D surface reconstruction fast & accurate! ๐Ÿš€ Projcet: https://t.co/SKJ7XRWTVt Arxiv:
Tweet card summary image
arxiv.org
Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumetric rendering...
@angelaqdai
Angela Dai
@angelaqdai
6 months
๐Ÿ“ข QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization @liuyuehcheng learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction! Project: https://t.co/mDgQxmhqkF
0
20
110
@angelaqdai
Angela Dai
@angelaqdai
4 months
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
@MattNiessner
Matthias Niessner
@MattNiessner
4 months
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 go๐Ÿš€๐Ÿš€๐Ÿš€ https://t.co/Rd4vDGiG5p
3
30
200
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
5 months
Check out the ScanNet++ workshop! Iโ€™ll be there tomorrow!
@angelaqdai
Angela Dai
@angelaqdai
5 months
Check out our ScanNet++ workshop @CVPR June 12 in 211 from 8:50am! Exciting keynotes on sota NVS & 3D understanding from Andrea Vedaldi @Oxford_VGG, @CordeliaSchmid, @GordonWetzstein, @K_S_Schwarz, @QianqianWang5, and leading methods on the benchmark! https://t.co/TvURvNYoW3
0
5
17
@MattNiessner
Matthias Niessner
@MattNiessner
5 months
๐Ÿ“ขCode Release of Pixel3DMM ๐Ÿ“ข Looking for a robust and accurate face tracker? Our state-of-the-art tracker handles challenging in-the-wild settings, such as extreme lighting conditions, fast movements, and occlusions. ๐Ÿ‘จโ€๐Ÿ’ป https://t.co/ynPtiaDvLF ๐ŸŒ https://t.co/2nsXxUKlK9
10
98
643
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
6 months
Submit your NVS sota method to the challenge!
@angelaqdai
Angela Dai
@angelaqdai
6 months
๐Ÿš€Join the ๐’๐œ๐š๐ง๐๐ž๐ญ++ ๐‚๐ก๐š๐ฅ๐ฅ๐ž๐ง๐ ๐ž @CVPR 2025! Think your method can handle large-scale 3D scenes? Put it to the test: https://t.co/TvURvNYoW3 Updates: โœ… Preprocessed, undistorted DSLR images โœ… 3DGS demo: https://t.co/8CP9KI3zLA by @liuyuehcheng, @chandan__yes
0
4
7
@angelaqdai
Angela Dai
@angelaqdai
9 months
๐Ÿ“ข ScanNet++ v2 Benchmark Release! ๐Ÿ† Test your state-of-the-art models on: ๐Ÿ”น Novel View Synthesis ๐Ÿ“ธโžก๏ธ๐Ÿ–ผ๏ธ ๐Ÿ”น 3D Semantic & Instance Segmentation ๐Ÿค–๐Ÿ”๐Ÿ•ถ๏ธ Shoutout to @chandan__yes and @liuyuehcheng for their incredible work๐Ÿ‘ ๐Ÿš€Check it out: https://t.co/SKCGM23hA0
2
42
203
@angelaqdai
Angela Dai
@angelaqdai
10 months
๐Ÿ“ขMeshArt: 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: https://t.co/aZPVyn8kQd
2
65
290
@manuel_dahnert
Manuel Dahnert
@manuel_dahnert
11 months
Super happy to present our #NeurIPS paper ๐‚๐จ๐ก๐ž๐ซ๐ž๐ง๐ญ ๐Ÿ‘๐ƒ ๐’๐œ๐ž๐ง๐ž ๐ƒ๐ข๐Ÿ๐Ÿ๐ฎ๐ฌ๐ข๐จ๐ง ๐…๐ซ๐จ๐ฆ ๐š ๐’๐ข๐ง๐ ๐ฅ๐ž ๐‘๐†๐ ๐ˆ๐ฆ๐š๐ ๐ž 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
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
1 year
Better optimizer for 3DGS!
@MattNiessner
Matthias Niessner
@MattNiessner
1 year
(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 ๐Ÿ‘๐ŸŽ% ๐Ÿ๐š๐ฌ๐ญ๐ž๐ซ ๐ญ๐ก๐š๐ง ๐Ÿ‘๐ƒ๐†๐’ for the same quality. https://t.co/F4uB4DpJGt https://t.co/Ju0Y2VxH7z
0
0
7
@angelaqdai
Angela Dai
@angelaqdai
1 year
How can we generate high-fidelity, complex 3D scenes? @QTDSMQ's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis! w/ @craigleili, @MattNiessner https://t.co/wv9bIhkkYi
3
77
318
@liuyuehcheng
Yueh-Cheng Liu
@liuyuehcheng
1 year
CAD retrieval with Diffusion!
@angelaqdai
Angela Dai
@angelaqdai
1 year
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
0
3
@angelaqdai
Angela Dai
@angelaqdai
1 year
Excited to present GenZI at #CVPR2024! @craigleili introduces GenZI, the first zero-shot approach to creating realistic 3D human-scene interactions by leveraging interaction priors from large VLMs. Code and data on our website! https://t.co/hUhMgUoU70 https://t.co/rnn1G5HOuu
1
25
102
@MattNiessner
Matthias Niessner
@MattNiessner
2 years
(1/2) LightIt: Illumination Modeling and Control for Diffusion Models! #CVPR2024 We facilitate lighting control for novel image generation from text prompts. We can also edit lighting for a given input image. Video: https://t.co/6aJU4Go5b3 Project: https://t.co/stjDU8TEOa
5
52
194
@angelaqdai
Angela Dai
@angelaqdai
2 years
Check out @DaoyiGao's DiffCAD - introducing probabilistic CAD retrieval and alignment to an RGB image. We captures ambiguities in depth/scale, inexact CAD matches, and don't require any training on real data! https://t.co/eFZgP9JP4j https://t.co/giMJl6R9Kl
2
40
137
@MattNiessner
Matthias Niessner
@MattNiessner
2 years
(1/2) Check out ๐†๐š๐ฎ๐ฌ๐ฌ๐ข๐š๐ง๐€๐ฏ๐š๐ญ๐š๐ซ๐ฌ: Photorealistic Head Avatars with Rigged 3D Gaussians! We create photorealistic head avatars by animating 3D Gaussians on a parametric face model - edited and rendered in *real-time*! https://t.co/R90VnWJB9Y https://t.co/Gv5gED01SG
14
200
902