Houyuan Chen
@chen_yuan76802
Followers
4
Following
12
Media
0
Statuses
10
Undergraduate @NJU1902 [email protected]
Joined April 2025
Wan-Animate: Unified Character Animation and Replacement with Holistic Replication Paper is out first! Other parts might not be ready yet, I'll post some demo test results later. https://t.co/MiOTZrusfd
Further news, video model increased from one to two. Tomorrow, I might test one of them. Welcome to provide some prompts.🫡 It appears from the examples I have that it's a model for generating reference videos from inputs, capable of handling multimodal inputs? Images or videos.
6
38
247
-- Peel the Wild -- Still obsessed with Kling 2.1 transitions 😍 Images cooked up with Seedream 4K [unlimited on Freepik!] + CapCut video Editor
68
83
805
TA-VLA: Torque-aware Vision-Language-Action models We show how to inject force cues into VLAs for contact-rich manipulation. Three takeaways: ✅Where: put torque adapters in the decoder, not the encoder. ✅How: use a single-token summary of torque history. ✅Why: jointly
9
57
452
nano banana is free and unlimited now you can edit image, swap actor from any film with it, turn to video with Veo 3 and Kling 2.1, make character talk.. they called it Higgsfield Swap-to-Video tutorial & examples:
197
756
10K
Ep2 is live. Guests: Chris Williamson & Jacky Zheng from Weta Workshop Truth bomb on AI in film: “I fear acceleration kills the LOVE of craft.” - Chris “Using AI? You’re in a constant BATTLE” - Jacky Will personalized AI stories ERASE water-cooler moments?
1
2
5
Thrilled to unveil LINO - Light of Normals! 🌟 We Achieve Up to 4K Resolution & 3D Scanner-Level Accurate Surface Normals Estimation. How? ☀️Learnable Light Register Tokens 🔬Preserve high-frequency details via Wavelet Sampling Try it at https://t.co/TfNH5aBeEs !
github.com
Contribute to houyuanchen111/LINO_UniPS development by creating an account on GitHub.
Light of Normals Unified Feature Representation for Universal Photometric Stereo
5
31
163
Combining VGGT with lighting registers gives rise to today’s strongest foundation model for photometric stereo. Thanks @_akhaliq for highlighting our work on LINO: predicting ultra-detailed 4K normal maps from unified features! 👀
Light of Normals Unified Feature Representation for Universal Photometric Stereo
1
10
64
Universal Photometric Stereo (PS) aims for robust normal maps under any light. 🚨 But big hurdles remain! 1️⃣ Deep coupling: Ambiguous intensity - is it the light changing or the surface turning? 🤔 2️⃣ Detail loss: Complex surfaces (shadows, inter-reflections, fine details) stump
1
11
36
Light of Normals Unified Feature Representation for Universal Photometric Stereo
1
31
90