Atti di CONVEGNO

Atti di CONVEGNO: [19328] Home page macrotipologia

Sfoglia

Prodotti recenti

1D/3D simulation procedure to investigate the potential of a lean burn hydrogen fuelled engine

Temporal Alignment for History Representation in Reinforcement Learning

Environments in Reinforcement Learning are usually only partially observable. To address this problem, a possible solution is to provide the agent with information about the past. However, providing complete observations of numerous steps can be excessive. Inspired by human memory, we propose to represent history with only important changes in the environment and, in our approach, to obtain automatically this representation using self-supervision. Our method (TempAl) aligns temporally-close f...

StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model

Despite the progress made in the style transfer task, most previous work focus on transferring only relatively simple features like color or texture, while missing more abstract concepts such as overall art expression or painter-specific traits. However, these abstract semantics can be captured by models like DALL-E or CLIP, which have been trained using huge datasets of images and textual documents. In this paper, we propose StylerDALLE, a style transfer method that exploits both of these mo...

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Generative Neural Radiance Field (GNeRF) models, which extract implicit 3D representations from 2D images, have recently been shown to produce realistic images representing rigid/semi-rigid objects, such as human faces or cars. However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications. This paper proposes a 3D-aware Semantic-Guided Generative Model (3D-SGAN) for hu...

Input Perturbation Reduces Exposure Bias in Diffusion Models

Denoising Diffusion Probabilistic Models have shown an impressive generation quality although their long sampling chain leads to high computational costs. In this paper, we observe that a long sampling chain also leads to an error accumulation phenomenon, which is similar to the exposure bias problem in autoregressive text generation. Specifically, we note that there is a discrepancy between training and testing, since the former is conditioned on the ground truth samples, while the latter is...

Scopri

Accesso al fulltext

no fulltext13811
reserved3231
open2174
partially open106
embargoed5
mixed1

Atti di CONVEGNO: [19328] Home page macrotipologia

Prodotti recenti

1D/3D simulation procedure to investigate the potential of a lean burn hydrogen fuelled engine

Temporal Alignment for History Representation in Reinforcement Learning

StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Input Perturbation Reduces Exposure Bias in Diffusion Models

Scopri

Tipologia

Autore

Data di pubblicazione

Editore

Rivista

Serie

Keyword

Lingua

Accesso al fulltext