6 papers
GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis
Thomas Tanay, Mohammed Brahimi, Michal Nazarczuk +5
Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors…
Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting
Arthur Moreau, Richard Shaw, Michal Nazarczuk +5
Feed-forward 3D Gaussian Splatting (3DGS) models enable real-time scene generation but are hindered by suboptimal pixel-aligned primitive placement, which relies on a dense, rigid…
ICo3D: An Interactive Conversational 3D Virtual Human
Richard Shaw, Youngkyoon Jang, Athanasios Papaioannou +4
This work presents Interactive Conversational 3D Virtual Human (ICo3D), a method for generating an interactive, conversational, and photorealistic 3D human avatar. Based on multi-v…
GASPACHO: Gaussian Splatting for Controllable Humans and Objects
Aymen Mir, Arthur Moreau, Helisa Dhamo +3
We present GASPACHO, a method for generating photorealistic, controllable renderings of human-object interactions from multi-view RGB video. Unlike prior work that reconstructs onl…
Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
Michal Nazarczuk, Thomas Tanay, Arthur Moreau +2
This paper presents a new dataset for Novel View Synthesis, generated from a high-quality, animated film with stunning realism and intricate detail. Our dataset captures a variety…
SCRREAM : SCan, Register, REnder And Map:A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
HyunJun Jung, Weihang Li, Shun-Cheng Wu +8
Traditionally, 3d indoor datasets have generally prioritized scale over ground-truth accuracy in order to obtain improved generalization. However, using these datasets to evaluate…