NTU LogoPVG Logo

Current Projects

NRF Fellowship, National Research Foundation

More ...

From Pixels to Physics: Integrating Physical Properties in Natural World Creation

National Research Foundation,  PI

The grant was awarded on 12/02/2025 (S$ 3,078,720.00), and started on 01/09/2025 and will end on 30/08/2030.

The aim of From Pixels to Physics is to create a realistic natural world adhering to physical principles, rather than dealing with only the realistic pixels as in traditional image, video, and 3D synthesis. Physics-based natural world creation is challenging because it requires a holistic interpretation of scenes and objects within it, including but not limited to appearance, geometry, motion, materials, collision, occlusion, gravity, interaction, mass, force and sound.

Artisan (arXiv'26)Physically grounded articulated 3D synthesis from text prompts and images

Articraft (NeurIPS'26)Agentic system for scalable generation of articulated 3D assets

Syn4D (ECCV'26)A large-scale synthetic multiview 4D dataset with dense annotations.

NOVA3R (ICLR'26)Non-pixel Aligned 3D reconstruction of visible and occluded regions from sparse views

NRF Fellowshipproject website

Finished Projects

Sony Focused Research Award

Vista4D: Feed-Forward 4D Scene Reconstruction from Any Monocular Video

Sony Research Award Program,  Co-PI, with Andrea Vedaldi

The grant was awarded on 30/03/2025 ($100,000), and started on 01/07/2025 and was end on 30/06/2026.

The aim of Vista4D is to obtain photorealistic 4D reconstructions of dynamic scenes from a single monocular video. To achieve this, Vista4D will develop a feed-forward neural network that, given as input a single monocular video, will output directly its 4D reconstruction

Sony Research Award Program

MSCA Fellowship

More ...

SYN3D: Synthesizing Photorealistic 3D Scene from Zero to One or Limited Views

MSCA Postdoctoral Fellowship (UKRI Horizon Europe),  PI, with Andrea Vedaldi

The grant was awarded on 13/02/2024 (£ 206,085.62), and started on 01/06/2024 and was end on 31/08/2025.

The aim of SYN3D is to enable the effortless creation of novel view synthesis and 3D reconstruction from limited views (from 0 to 5) in a feed-forward manner. In general, such a few input views do not contain sufficient information for compressive 3D synthesis. However, our scientific hypothesis is that 3D synthesis from limited views is still possible by learning, from billion images, the capability of hallucinating unobserved parts of 3D objects/scenes, thus obtaining plausible if not faithful reconstructions.

MVSplat, MVSplat-360Feed-forward 3D scene synthesis from limited views (even for 360 degree)

Free3DFeed-forward 3D object synthesis from a single image for open-set categories

MSCA Postdoctoral Fellowshipproject website