Papers

S-NeRF: Neural Radiance Fields for Street Views Members Public

In this paper, the authors propose a new street-view NeRF (S-NeRF) that considers novel view synthesis of both the large-scale background scenes and the foreground moving vehicles jointly. Learn more about their approach and the results of experiments!

Sophia
Sophia
Papers

Universal Guidance for Diffusion Models Members Public

Typical diffusion models cannot be conditioned on other modalities without retraining. This work presents a universal guidance algorithm that enables diffusion models to be controlled by arbitrary guidance modalities without the need to retrain any use-specific components.

Sophia
Sophia
Papers

3D Generation on ImageNet Members Public

In this paper, the authors develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to challenging datasets, like ImageNet. It is based on three new ideas. Learn them!

Sophia
Sophia
Papers

3D-aware Conditional Image Synthesis Members Public

This paper describes a 3D-aware conditional generative model for controllable photorealistic image synthesis. It integrates 3D representations with conditional generative modeling, i.e., enabling controllable high-resolution 3D-aware rendering by conditioning on user inputs.

Sophia
Sophia
Papers

SinMDM: Single Motion Diffusion Members Public

This paper presents a Single Motion Diffusion Model, dubbed SinMDM, a model designed to learn the internal motifs of a single motion sequence with arbitrary topology and synthesize motions of arbitrary length that are faithful to them. Check it out!

Sophia
Sophia
Papers

LEGO-Net: Learning Regular Rearrangements of Objects in Rooms Members Public

LEGO-Net is a data-driven transformer-based iterative method for LEarning reGular rearrangement of Objects in messy rooms. Results demonstrate that the method is able to reliably rearrange room scenes and outperform other methods. Find out more!

Sophia
Sophia
Papers

OmniObject3D Members Public

OmniObject3D is a large vocabulary 3D object dataset featuring massive high-quality real-scanned 3D objects that can be used to facilitate the development of 3D perception, reconstruction, and generation in the real world. Give it a try!

Sophia
Sophia
Papers

MEGANE: Morphable Eyeglass and Avatar Network Members Public

Megane is a 3D compositional morphable model of eyeglasses that incorporates high-fidelity geometric and photometric interaction effects. To support the variation in eyeglass topology, a hybrid representation of surface geometry and a volumetric representation is employed.

Sophia
Sophia
Papers