Related papers: ELITE: Efficient Gaussian Head Avatar from a Monoc…

Speech-driven talking heads have recently emerged and enable interactive avatars. However, real-world applications are limited, as current methods achieve high visual fidelity but slow or fast yet temporally unstable. Diffusion methods…

We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D Gaussian splats, and simultaneously builds a compressed…

We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality Gaussian-based full-body avatars from multi-view video. However, these methods require…

The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives. Constructing such avatars is a challenging research problem, due…

Although neural rendering has made significant advances in creating lifelike, animatable full-body and head avatars, incorporating detailed expressions into full-body avatars remains largely unexplored. We present DEGAS, the first 3D…

Real-time text-driven joint audio-video avatar generation requires jointly synthesizing portrait video and speech with high fidelity and precise synchronization, yet existing audio-visual diffusion models remain too slow for interactive use…

Diffusion-based models have gained wide adoption in the virtual human generation due to their outstanding expressiveness. However, their substantial computational requirements have constrained their deployment in real-time interactive…

In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can help generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their…

With recent advancements in neural rendering and motion capture algorithms, remarkable progress has been made in photorealistic human avatar modeling, unlocking immense potential for applications in virtual reality, augmented reality,…

Synthesizing novel views of large-scale scenes from unconstrained in-the-wild images is an important but challenging task in computer vision. Existing methods, which optimize per-image appearance and transient occlusion through implicit…

We present InstantGeoAvatar, a method for efficient and effective learning from monocular video of detailed 3D geometry and appearance of animatable implicit human avatars. Our key observation is that the optimization of a hash grid…

We present an efficient text-to-video generation framework based on latent diffusion models, termed MagicVideo. MagicVideo can generate smooth video clips that are concordant with the given text descriptions. Due to a novel and efficient 3D…

We present Drivable 3D Gaussian Avatars (D3GA), a multi-layered 3D controllable model for human bodies that utilizes 3D Gaussian primitives embedded into tetrahedral cages. The advantage of using cages compared to commonly employed linear…

The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance, existing…

We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a…

Rendering dynamic scenes from monocular videos is a crucial yet challenging task. The recent deformable Gaussian Splatting has emerged as a robust solution to represent real-world dynamic scenes. However, it often leads to heavily redundant…

Sparse-view 3D Gaussian splatting seeks to render high-quality novel views of 3D scenes from a limited set of input images. While recent pose-free feed-forward methods leveraging pre-trained 3D priors have achieved impressive results, most…

3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain primarily constrained by current paradigms and the scarcity…

This paper addresses the limitations of existing 3D Gaussian Splatting (3DGS) methods, particularly their reliance on adaptive density control, which can lead to floating artifacts and inefficient resource usage. We propose a novel densify…

We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. Existing methods either involve time-consuming optimization for a specific person with multiple images, or they struggle to synthesize…