Abstract The recent Gaussian Splatting achieves high-quality and real-time novel-view
synthesis of the 3D scenes. However, it is solely concentrated on the appearance and …

Realistic 3D human generation from text prompts is a desirable yet challenging task.
Existing methods optimize 3D representations like mesh or neural fields via score distillation …

Despite the great success in 2D editing using user-friendly tools, such as Photoshop,
semantic strokes, or even text prompts, similar capabilities in 3D areas are still limited, either …

We present Neural Feature Fusion Fields (N3F),\a method that improves dense 2D image
feature extractors when the latter are applied to the analysis of multiple images …

We present vMAP, an object-level dense SLAM system using neural field representations.
Each object is represented by a small MLP, enabling efficient, watertight object modelling …

Existing 3D-aware image synthesis approaches mainly focus on generating a single
canonical object and show limited capacity in composing a complex scene containing a …

Abstract Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene
representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable …

In recent years, neural implicit surface reconstruction has emerged as a popular paradigm
for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural …

Animating high-fidelity video portrait with speech audio is crucial for virtual reality and digital
entertainment. While most previous studies rely on accurate explicit structural information …

In this paper, we study the problem of 3D scene geometry decomposition and manipulation
from 2D views. By leveraging the recent implicit neural representation techniques …