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.
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!
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!
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!
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.
GLIGEN (Grounded-Language-to-Image Generation) is a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs. Take a closer look!
StyleGAN-T addresses the specific requirements of large-scale text-to-image synthesis to significantly improve over previous GANs and outperform distilled diffusion models in terms of sample quality and speed. Learn more about the model!
HyperReel is a novel 6-DoF video representation that is unique compared to other approaches in that it both accelerates volume rendering and improves rendering quality, especially for challenging view dependent scenes. Find out more about it!
In this work, the authors address the robustness issue of dynamic radiance field reconstruction methods by jointly estimating the static and dynamic radiance fields along with the camera parameters (poses and focal length). Learn how they do it!
AgileAvatar is a novel self-supervised learning framework to create high-quality stylized 3D avatars with a mix of continuous and discrete parameters. To ensure the discrete parameters are optimized, a cascaded relaxation-and-search pipeline is implemented.
Box2Mask is a novel single-shot instance segmentation approach, which integrates the classical level-set evolution model into deep neural network learning to achieve accurate mask prediction with only bounding box supervision. Check the paper out!
Dream Fields can generate the geometry and color of a wide range of objects without 3D supervision. It combines neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions. Take a look!