Chenguo Lin (@lin_chenguo)

Pinned

C

Chenguo Lin@lin_chenguo · Jul 15

🚨 We just released 🎞️MoVieS — a feed-forward model that reconstructs 4D scenes in ⚡️1 second My favorite part: It learns dense (pixel-wise) sharp 3D world movements from novel view rendering + sparse point tracking supervision 🤯🎯 Check it out 👉 chenguolin.github.io/projects/MoVieS

2

32

159

80

20.0K

Chenguo Lin Retweeted

E

Emm | scenario.com@emmanuel_2m · Jul 22

"Generate in Parts" just got better with "Split in Parts"! 🥹😇 @hervenivon added a toggle in the @Scenario_gg 3D viewer that instantly splits generated meshes into an exploded view. See how PartCrafted breaks down your model - no need to download and check in Blender anymore.

11

31

312

161

15.0K

Chenguo Lin Retweeted

K

Kwang Moo Yi@kwangmoo_yi · Jul 22

Preprint of (not) today: Lin and Lin et al., "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second" -- chenguolin.github.io/projects/MoVie… Feed-forward VGGT + Splats/Motion estimation heads, trained also with rendering & motion estimation losses. Multitask training improves all.

0

7

79

30

4.0K

Chenguo Lin Retweeted

E

Emm | scenario.com@emmanuel_2m · Jul 21

Beyond thrilled to officially roll out "Generate in Parts" on app.scenario.com - a new standard for Image-to-3D workflows! Say goodbye to monolithic Al meshes, and hello to clean, modular 3D assets you can animate, edit, or 3D print. Let's dive in with #PartCrafter👇!

33

107

692

534

57.0K

Chenguo Lin Retweeted

E

Emm | scenario.com@emmanuel_2m · Jul 20

"Generate in Parts" is so insanely good, it even generated the bullets inside the cylinder - automatically, from a single image. Every part comes cleanly separated: barrel, cylinder, trigger, hammer, etc… The future of 3D AI goes live next week on app.scenario.com 🔥

21

46

638

523

34.0K

Chenguo Lin Retweeted

c

camenduru@camenduru · Jul 20

🧩 PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers 📐 Jupyter Notebook 🥳 Thanks to @kevin_yuchenlin ❤ @lin_chenguo ❤ @paulpanwang ❤ Honglei Yan ❤ Yiqiang Feng ❤ Yadong Mu ❤ Katerina Fragkiadaki ❤ Thanks to @alexandernasa ❤…

5

17

83

46

3.0K

C

Chenguo Lin@lin_chenguo · Jul 19

Just found a great product-ready implementation of our PartCrafter (wgsxm.github.io/projects/partc…) 🤩 Can't wait to try it!

EEmm | scenario.com@emmanuel_2m · Jul 18

Say goodbye to monolithic AI meshes! 👋 We're rolling out "Generate in Parts" for 3D models on app.scenario.com, next week. Things will get modular. ⚙ Another wild update! :) 🚀

1

11

63

29

3.0K

Chenguo Lin Retweeted

A

Alexandre Morgand@Almorgand · Jul 18

"🎞️MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second" TL;DR: Feed-forward framework that jointly reconstructs appearance, geometry and motion for 4D scene perception from monocular videos in one second.

2

11

95

71

5.0K

C

Chenguo Lin@lin_chenguo · Jul 15

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second

CChenguo Lin@lin_chenguo · Jul 15

🚨 We just released 🎞️MoVieS — a feed-forward model that reconstructs 4D scenes in ⚡️1 second My favorite part: It learns dense (pixel-wise) sharp 3D world movements from novel view rendering + sparse point tracking supervision 🤯🎯 Check it out 👉 chenguolin.github.io/projects/MoVieS

3

13

168

84

10.0K

Chenguo Lin Retweeted

A

AK@_akhaliq · Jul 15

MoVieS Motion-Aware 4D Dynamic View Synthesis in One Second

3

15

129

80

29.0K

Chenguo Lin Retweeted

Z

Zhenjun Zhao@zhenjun_zhao · Jul 15

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second @lin_chenguo, @kevin_yuchenlin, @paulpanwang, @markyu98, Honglei Yan, @KaterinaFragiad, Yadong Mu tl;dr: dynamic splatter pixels->renderable deforming 3D particles->3D dynamic scenes arxiv.org/abs/2507.10065

0

7

24

15

2.0K

C

Chenguo Lin@lin_chenguo · Jul 15

We just found a wonderful Huggingface🤗 space demo for 🧩PartCrafter made by @alexandernasa. Thank you very much🤩 !!! If you'd like to generate 3D objects in parts, try it out! It's super simple & fast & free: huggingface.co/spaces/alexnas…

lin_chenguo's tweet card. PartCrafter - a Hugging Face Space by alexnasa

0

1

8

1

363

C

Chenguo Lin@lin_chenguo · Jul 13

💥 We just open-sourced the inference & training code of PartCrafter 🧩 — along with pretrained checkpoints! 🚀 Check it out here 👉 wgsxm.github.io/projects/partc… ❗️❗️ #OpenSource #3D #Diffusion #AI #PartCrafter

CChenguo Lin@lin_chenguo · Jun 9

🚨 New drop: PartCrafter 🧩 A 3D-native DiT that generates 3D objects in parts 👉 wgsxm.github.io/projects/partc… The most exciting part for me: 🌟 We realised most 3D datasets already come with part-structured meshes — but previous works just ignored that. 🤯 Simple & Effective 🚀

0

2

24

17

2.0K

Chenguo Lin Retweeted

M

Min Choi@minchoi · Jun 12

ByteDance and Carnegie Mellon researchers just announced PartCrafter This AI turns a single photo into fully editable 3D parts in seconds 10 wild examples:

118

815

8.0K

6.0K

954.0K

Chenguo Lin Retweeted

A

AK@_akhaliq · Jun 9

PartCrafter Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

11

188

2.0K

1.0K

120.0K

C

Chenguo Lin@lin_chenguo · Jun 9

🚨 New drop: PartCrafter 🧩 A 3D-native DiT that generates 3D objects in parts 👉 wgsxm.github.io/projects/partc… The most exciting part for me: 🌟 We realised most 3D datasets already come with part-structured meshes — but previous works just ignored that. 🤯 Simple & Effective 🚀

1

2

11

4

2.0K

C

Chenguo Lin@lin_chenguo · Jun 9

Still waiting for @DeemosTech Gen-2 to generate 3D objects in parts? 🫠 We just dropped an open-source solution that actually understands 3D structure 🧠💥 ✅ No extra segmentation ✅ Pure 3D-native DiT 🎯 Generates part-aware 3D objects out of the box Check it now 👇

YYuchen Lin@kevin_yuchenlin · Jun 9

🚀 Introducing PartCrafter – a breakthrough in 3D generation! From just one RGB image, it generates multiple structured, semantically meaningful 3D parts — all in one unified pass, no pre-segmentation needed. Paper: arxiv.org/abs/2506.05573 Project Page: wgsxm.github.io/projects/partc…

1

0

7

0

322

Chenguo Lin Retweeted

J

Jon Barron@jon_barron · Apr 28

Here's my 3DV talk, in chapters: 1) Intro / NeRF boilerplate. 2) Recent reconstruction work. 3) Recent generative work. 4) Radiance fields as a field. 5) Why generative video has bitter-lessoned 3D. 6) Why generative video hasn't bitter-lessoned 3D. 5 & 6 are my favorites.

37

99

729

661

88.0K

C

Chenguo Lin@lin_chenguo · Apr 23

Just arrived in Singapore for #ICLR2025! 🌴🇸🇬 Excited to present "DiffSplat" (github.com/chenguolin/Dif…) on Friday and connect with everyone at the conference. Let’s talk 3D vision, spatial intelligence, AIGC, and everything in between -- see you there! 👋✨

lin_chenguo's tweet image. Just arrived in Singapore for #ICLR2025! 🌴🇸🇬

Excited to present "DiffSplat" (github.com/chenguolin/Dif…) on Friday and connect with everyone at the conference.

Let’s talk 3D vision, spatial intelligence, AIGC, and everything in between -- see you there! 👋✨

0

5

0

424