Xiaoyang Wu @XiaoyangWu_ Twitter profile

Pinned Tweet

Xiaoyang Wu

2 months

I am so happy that PTv3 was selected as one of the Oral papers (90/11,532) of #CVPR2024 . PTv2 is my first paper and the first paper accepted by a top conference. It really means a lot that PTv3 became my first Oral paper! Love you, CVPR!

Xiaoyang Wu

@XiaoyangWu_

5 months

Our new method Point Transformer V3 (PTv3), a stride toward a simpler, faster, and stronger design of 3D transformers, is now available in ArXiv (). This is a joint effort with Li Jiang, @PengshuaiWang , @zhijianliu_ , @HengshuangZhao

2

3

14

1

16

Last Seen Profiles

@QueenbeeWeb3

@prodigyallstars

@Hoontair_

@RadioCityRad

@finplan

@b4itwascool2bme

@bar_tv

@KingJay93840263

@driccos

@axlakas

@andotvu

@Richard30737777

@Stravinskas2023

@ThomasASex_Girl

@CuXCnD85kWZnuRL

@pulpitofluffy

@qrtrmusic

@TBazzana

@Parcafnbr

@ForrestHarding4

@PDXDiamondProj

@scehnic

@tokinspb

@Coco_Latex_

@spoilluxxxx

@KaitlynPallozzi

@Apraiser63

@C00K130R30

@mmdlkmly17

@AkemiHomura8205

@abesuke0604

@momo_yunn

@KorevLager

@AntonioSir78857

@_LeShawnJohnson

@suzuha821068105

Xiaoyang Wu

@XiaoyangWu_

3 months

#CVPR2024 Happy to announce that our 8 submissions (2 first-author) are all accepted by CVPR24.

8

5

398

Xiaoyang Wu

@XiaoyangWu_

1 year

I am really glad to be named a CVPR'23 outstanding reviewer as my first time serving as a reviewer. Thank you! @CVPR

2

3

98

Xiaoyang Wu

@XiaoyangWu_

5 months

Paper: Project: Code: Weight: Thanks @_akhaliq for inviting us to release the model weight with the Hugging Face model card.

0

8

21

Xiaoyang Wu

@XiaoyangWu_

5 months

Our new method Point Transformer V3 (PTv3), a stride toward a simpler, faster, and stronger design of 3D transformers, is now available in ArXiv (). This is a joint effort with Li Jiang, @PengshuaiWang , @zhijianliu_ , @HengshuangZhao

2

3

14

Xiaoyang Wu

@XiaoyangWu_

2 months

From #CVPR2023 to #CVPR2024 , Pointcept, 1 year, 10 papers, 100 forks, 1000 stars! 🎉🎉🎉

Xiaoyang Wu

@XiaoyangWu_

1 year

#CVPR23 Introducing Pointcept, a codebase for point cloud perception research. Pointcept is a highly potent tool, as evidenced by its ability to boost the base semseg result of SpUnet on the ScanNet val set, resulting in an impressive 75.0%+ mIoU. GitHub:

0

1

0

16

Xiaoyang Wu

@XiaoyangWu_

3 months

#CVPR Our PTv3 is accepted by CVPR24, especially thanks to efforts from our coauthors! @PengshuaiWang @zhijianliu_ @HengshuangZhao . We will also have a tutorial related to Point Cloud Understanding in @CVPR 2024, more information will be available soon!

AK

@_akhaliq

5 months

Point Transformer V3: Simpler, Faster, Stronger paper page: This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of

2

50

288

0

1

6

Xiaoyang Wu

@XiaoyangWu_

1 year

Four papers are accepted by CVPR 2023! #CVPR2023

0

1

8

Xiaoyang Wu

@XiaoyangWu_

3 months

#CVPR Point Prompt Training (PPT) is also accepted by CVPR 24, thanks to contribution from our co-authors! @HengshuangZhao

Xiaoyang Wu

@XiaoyangWu_

9 months

Check our new work Point Prompt Training (PPT), a novel pre-training framework for 3D multi-dataset synergistic learning. PPT attains SOTA results across over ten tasks spanning both indoor and outdoor 3D scenarios. ArXiv: Code:

0

4

0

1

7

Xiaoyang Wu

@XiaoyangWu_

1 year

Happy to announce our #CVPR2023 work, Masked Scene Contrast (MSC)! Inspired by PointContrast and MAE, we directly operate CL and MPM on the point cloud. MSC boosted SparseUNet validation result on ScanNet to 75.5% Arxiv: Code:

0

1

5

Xiaoyang Wu

@XiaoyangWu_

9 months

Check our new work Point Prompt Training (PPT), a novel pre-training framework for 3D multi-dataset synergistic learning. PPT attains SOTA results across over ten tasks spanning both indoor and outdoor 3D scenarios. ArXiv: Code:

0

4

Xiaoyang Wu

@XiaoyangWu_

2 months

@CVPR Every day I search “cvpr 24 oral”, I get a link to this poster.

1

0

4

Xiaoyang Wu

@XiaoyangWu_

2 months

@CVPR Good to see the email just before going to sleep. (4AM in HK)

0

2

Xiaoyang Wu

@XiaoyangWu_

6 months

@CVPR 24-hour countdown, ready to no sleeping!

0

2

Xiaoyang Wu

@XiaoyangWu_

3 months

@bardh95 LOL, thank you! It is time to slow down and do something really meaningful to our community.

0

1

Xiaoyang Wu

@XiaoyangWu_

3 months

@Reesharkcong Thanks for your appreciation. See you in Seattle!

0

1

Xiaoyang Wu

@XiaoyangWu_

2 months

@JeromeRevaud So pity! We love your paper, DUSt3R. It is simple, elegant and instructive.

0

1

Xiaoyang Wu

@XiaoyangWu_

1 year

#CVPR23 Introducing Pointcept, a codebase for point cloud perception research. Pointcept is a highly potent tool, as evidenced by its ability to boost the base semseg result of SpUnet on the ScanNet val set, resulting in an impressive 75.0%+ mIoU. GitHub:

0

1

Xiaoyang Wu

@XiaoyangWu_

3 months

@deep_Ayami Exactly! I also love CVPR as always.

0

1

Xiaoyang Wu

@XiaoyangWu_

2 months

Cool!

AK

@_akhaliq

2 months

Garment3DGen 3D Garment Stylization and Texture Generation We introduce Garment3DGen a new method to synthesize 3D garment assets from a base mesh given a single input image as guidance. Our proposed approach allows users to generate 3D textured clothes based on both

5

48

238

0

1

Xiaoyang Wu

@XiaoyangWu_

3 months

@CVPR @NeurIPSConf Forgive my joke~ I love CVPR!

0

1