Fangneng Zhan

Assistant Professor | HKUST
World Mind Lab:

[kaichen_zhou @alex_kai2020]

🚀 CFP: 1st Workshop on #PhysWorldAI at #NeurIPS2026!

Explore physical geometry, physical properties, multimodal sensing & embodied AI.

🎤 Keynotes: Anandkumar, Snavely, Finn & Freeman.

📍Atlanta, Dec 12/13 | 📅 Due Sept 9

https://t.co/A0iuxtCUyc

[kaichen_zhou @alex_kai2020]

🚀 Stream3D is accepted to CVPR-W 2026!

The first framework for long-horizon 3D asset generation from monocular streams 🌊
— turning frozen 3D generators into streaming generators via evidential memory, no retraining

📈 Better consistency across long streams
💾 Constant memory footprint

📃 https://t.co/acp9Gydt2t

@MIT @Harvard @medialab @hkust
#AI #ComputerVision #3D

[kaichen_zhou @alex_kai2020]

Congrats to VGGT-Omega and D4TR! 🎉

Great to see 4D reconstruction gaining more attention.

VGGT-Omage sets a strong benchmark.

Page-4D (ICLR 2026) uses the same inference backbone as VGGT, with open-source code, and still performs reasonably well in indoor scenarios. ✨
https://t.co/xY1i0IQXVA

[Charles @Keming_Charles]

Excited to share our new roadmap:

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

What does it mean for image generation models to become truly intelligent?

HF Daily Paper: https://t.co/jnC75XxbGf
WebPage: https://t.co/cB510BFxfp

[Adam Kortylewski @AdamKortylewski]

Got a paper on generative models accepted at CVPR 2026?

Share it with us at the 4th Workshop on Generative Models for Computer Vision!

https://t.co/zwzwRvD4o8

You can simply submit your accepted CVPR paper, no need to reformat!

Deadline: April 30 (AoE)

[kaichen_zhou @alex_kai2020]

🚀 PAGE-4D is out! (ICLR 2026)

We bring VGGT into the dynamic world 🌍
— disentangling pose & geometry for 4D perception

📈 SOTA across dynamic scene benchmarks
💻 Training + evaluation code fully released

📃 https://t.co/rUSzgLJqsW

@MIT @Harvard @medialab

#AI #ComputerVision #4D

[Zhenjun Zhao @zhenjun_zhao]

MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation

Muyu Xu, Fangneng Zhan, Xiaoqin Zhang, Ling Shao, Shijian Lu

tl;dr: multi-scale depth-wise convolutions->transformer; batch-wise encoding and decoding

https://t.co/3H9KEqRs58

[Kosta Derpanis at #ECCV2026 🇸🇪 @CSProfKGD]

Coming soon to a geometric problem near you @vincesitzmann

[Zhenjun Zhao @zhenjun_zhao]

PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception

Kaichen Zhou, Yuhan Wang, Grace Chen, Xinhai Chang, Gaspard Beaudouin, @fnzhan0507, Paul Pu Liang, Mengyu Wang

tl;dr: dynamic VGGT

https://t.co/NK7LEkKkr9

[Zhenjun Zhao @zhenjun_zhao]

Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey

Jiahui Zhang, Yuelei Li, @AnpeiC, Muyu Xu, Kunhao Liu, @jianyuan_wang, @xxlong0, @hx_liang95, @zexiangxu, @haosu_twitr, Christian Theobalt, Christian Rupprecht, Andrea Vedaldi, @hpfister, Shijian Lu, @fnzhan0507

tl;dr: in title

https://t.co/AD0w8TBgZG

[MrNeRF @janusch_patas]

Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey

Abstract (excerpt):
This survey offers a comprehensive review of feed-forward techniques for u3D reconstruction and view synthesis. It provides a taxonomy based on underlying representation architectures, including point cloud, 3D Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), etc.

We examine key tasks such as pose-free reconstruction, dynamic 3D reconstruction, and 3D-aware image and video synthesis, highlighting their applications in digital humans, SLAM, robotics, and beyond. Additionally, we review commonly used datasets with detailed statistics and evaluation protocols for various downstream tasks.

We conclude by discussing open research challenges and promising directions for future work, emphasizing the potential of feed-forward approaches to advance the state of the art in 3D vision.

[Adam Kortylewski @AdamKortylewski]

Submit your extended abstract to our workshop on "Generative Models for Computer Vision"
#CVPR2025 @CVPR

Authors with accepted CVPR papers are welcome to present their poster as well!

Deadline: April 25th

We also have an incredible speaker line-up!

[MrNeRF @janusch_patas]

Visual Acoustic Fields

Contributions:
• The impact locations of collected visual-sound pairs can be localized in 3D space by learning a radiance field with synchronized camera poses.

• Predicted impact sounds in our Visual Acoustic Fields accurately align with the corresponding impact locations.

• Impact regions or objects can be precisely retrieved with sound using our Visual Acoustic Fields.

[Fangneng Zhan @fnzhan0507]

@agigiraffe @jon_barron Sure, all components are modeled by Blender with some simple rotation (for objects) and particle path (for 3D Gaussians) animations.

[Fangneng Zhan @fnzhan0507]

@jon_barron Thank you!

[Jon Barron @jon_barron]

I've never seen a more polished paper teaser video than this one. The 3D Gaussians even cast shadows!

[Jakob Troidl @jakobtroidl]

📢Our latest preprint shows that learning global neuron shapes can help to automatically proofread connectomes and predict neuron types. https://t.co/v39Zm5Igo1 Work done in collaboration with @HHMIJanelia, @srinituraga & @HarvardVCG #connectomics #AI 🧵(1/n)

[Adam Kortylewski @AdamKortylewski]

Fully packed 🥳

[Fangneng Zhan @fnzhan0507]

@VcaiMpi @BenMildenhall @GordonWetzstein @vincesitzmann @yiyi_liao_ @MattNiessner @haosu_twitr @CVPR #CVPR

[VCAI - MPI for Informatics @VcaiMpi]

Join our workshop on Neural Rendering Intelligence today at 1:30 pm in Summit 332 to see the latest advances in neural rendering!
Exciting keynote speakers! More info at
https://t.co/wRN0jA34sx
@BenMildenhall @GordonWetzstein @vincesitzmann @yiyi_liao_ @MattNiessner @haosu_twitr