Hanxue Liang
@hx_liang95
Followers
60
Following
95
Statuses
24
PhD student at @Cambridge_Uni, looking for full-time positions, please DM if you know any openings. 3D/4D Reconstruction/Generation, On-device MoE, Point Cloud
Cambridge
Joined September 2021
RT @deepseek_ai: 🚀 DeepSeek-R1 is here! ⚡ Performance on par with OpenAI-o1 📖 Fully open-source model & technical report 🏆 MIT licensed: D…
0
8K
0
RT @WayneINR: 🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing…
0
65
0
RT @hx_liang95: 🚀Excited to Introduce #BTimer: Real-Time Dynamic Scene Reconstruction from Monocular Videos! Struggling with novel view…
0
16
0
@HuanLing6 @jiawei6_ren @huangjh_hjh Thanks for your guidance on the project! Really nice collaboration experience!
0
0
0
RT @janusch_patas: Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos TL;DR: We present the first feed-forwar…
0
11
0
RT @WilliamLamkin: BTimer: Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos website:
0
2
0
1
0
4
#Btimer Our 3-stage curriculum training on a mix of static and dynamic data drives strong generalization: 1️⃣ Low-res to high-res static pretraining 2️⃣ Dynamic scene co-training 3️⃣ Long-context window fine-tuning ⚡ BTimer Retains static scene excellence with bullet-time formulation & outperforms baselines like GS-LRM on Tanks & Temples!
0
0
1
RT @huangjh_hjh: 📢Please check out our newest work on feed-forward reconstruction of dynamic monocular videos! With our bullet-time formula…
0
9
0
A heartfelt thanks to all co-authors for their incredible contributions and supervision🙌 @jiawei6_ren @ashmrz10 @abtorralba @liuziwei7 @igilitschenski @FidlerSanja @CengizOztireli @HuanLing6 @ZGojcic @huangjh_hjh
0
0
3
RT @ZGojcic: Reconstruct and explore monocular dynamic videos in real time! Interaction with your favorite video content is now possible w…
0
2
0
RT @RadianceFields: New research from @NVIDIAAIDev. Generate per-frame 3D "bullet-time" scenes from regular video in just 150ms on a single…
0
10
0