Search Results for author:
Found 10 papers, 5 papers with code
Towards Controllable Face Generation with Semantic Latent Diffusion Models
To address that, in this paper we propose a SIS framework based on a novel Latent Diffusion Model architecture for human face generation and editing that is both able to reproduce and manipulate a real reference image and generate diversity-driven results.
Informative Rays Selection for Few-Shot Neural Radiance Fields
Neural Radiance Fields (NeRF) have recently emerged as a powerful method for image-based 3D reconstruction, but the lengthy per-scene optimization limits their practical usage, especially in resource-constrained settings.
Semantic Image Synthesis via Class-Adaptive Cross-Attention
Thus, they tend to overlook global image statistics, ultimately leading to unconvincing local style editing and causing global inconsistencies such as color or illumination distribution shifts.
Automatic Generation of Semantic Parts for Face Image Synthesis
Also, we show our model can be put before a SIS generator, opening the way to a fully automatic generation control of both shape and texture.
Memory-augmented Online Video Anomaly Detection
The ability to understand the surrounding scene is of paramount importance for Autonomous Vehicles (AVs).
Learning Neural Radiance Fields from Multi-View Geometry
We present a framework, called MVG-NeRF, that combines classical Multi-View Geometry algorithms and Neural Radiance Fields (NeRF) for image-based 3D reconstruction.
Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians
Generating dense point clouds from sparse raw data benefits downstream 3D understanding tasks, but existing models are limited to a fixed upsampling ratio or to a short range of integer values.
Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction
In this paper, a complete pipeline for image-based 3D reconstruction of urban scenarios is proposed, based on PatchMatch Multi-View Stereo (MVS).
Efficient View Clustering and Selection for City-Scale 3D Reconstruction
Image datasets have been steadily growing in size, harming the feasibility and efficiency of large-scale 3D reconstruction methods.
Leveraging Local Domains for Image-to-Image Translation
Our comprehensive evaluation setting shows we are able to generate realistic translations, with minimal priors, and training only on a few images.
