Sibi Catley-Chandar — accepted AI-conference papers

2025

ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs

Michal Nazarczuk, Sibi Catley-Chandar, Thomas Tanay, Zhensong Zhang, Gregory Slabaugh, Eduardo Pérez-Pellitero

NeurIPS 2025poster

Dynamic Novel View Synthesis aims to generate photorealistic views of moving subjects from arbitrary viewpoints. This task is particularly challenging when relying on monocular video, where disentangling structure from motion is ill-posed and supervision is scarce. We introduce Video Diffusion-Aware…

Cited by 0 Source ↗Scholar ↗

2024

SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting

Richard Shaw*, Michal Nazarczuk, Jifei Song, Arthur Moreau, Sibi Catley-Chandar, Helisa Dhamo +1

ECCV 2024poster

"Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling interactive viewing at real-time frame rates. However, it…

Cited by 11 Source ↗PDF ↗Scholar ↗