Junfeng Ni

Publications

G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior

VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video

3D Scene Change Modeling with Consistent Multi-View Aggregation

DreamArt: Generating Interactable Articulated Objects from a Single Image

Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing

TACO: Taming Diffusion for in-the-wild Video Amodal Completion

Decompositional Neural Scene Reconstruction with Generative Diffusion Prior

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

PhyRecon: Physically Plausible Neural Scene Reconstruction

Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture

Publications

G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior

VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Video

3D Scene Change Modeling with Consistent Multi-View Aggregation

DreamArt: Generating Interactable Articulated Objects from a Single Image

Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing

TACO: Taming Diffusion for in-the-wild Video Amodal Completion

Decompositional Neural Scene Reconstruction with Generative Diffusion Prior

MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

PhyRecon: Physically Plausible Neural Scene Reconstruction

Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture