Recent advances in 3d gaussian splatting
The emergence of 3D Gaussian splatting (3DGS) has greatly accelerated rendering in novel
view synthesis. Unlike neural implicit representations like neural radiance fields (NeRFs) …
view synthesis. Unlike neural implicit representations like neural radiance fields (NeRFs) …
Adversarial diffusion distillation
Abstract We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that
efficiently samples large-scale foundational image diffusion models in just 1–4 steps while …
efficiently samples large-scale foundational image diffusion models in just 1–4 steps while …
Lavie: High-quality video generation with cascaded latent diffusion models
This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a
pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task …
pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task …
Align your gaussians: Text-to-4d with dynamic 3d gaussians and composed diffusion models
Text-guided diffusion models have revolutionized image and video generation and have
also been successfully used for optimization-based 3D object synthesis. Here we instead …
also been successfully used for optimization-based 3D object synthesis. Here we instead …
Fast high-resolution image synthesis with latent adversarial diffusion distillation
Diffusion models are the main driver of progress in image and video synthesis, but suffer
from slow inference speed. Distillation methods, like the recently introduced adversarial …
from slow inference speed. Distillation methods, like the recently introduced adversarial …
Evaluating text-to-visual generation with image-to-text generation
Despite significant progress in generative AI, comprehensive evaluation remains
challenging because of the lack of effective metrics and standardized benchmarks. For …
challenging because of the lack of effective metrics and standardized benchmarks. For …
Sparsectrl: Adding sparse controls to text-to-video diffusion models
The development of text-to-video (T2V), ie, generating videos with a given text prompt, has
been significantly advanced in recent years. However, relying solely on text prompts often …
been significantly advanced in recent years. However, relying solely on text prompts often …
Factorizing text-to-video generation by explicit image conditioning
Abstract We present Emu Video, a text-to-video generation model that factorizes the
generation into two steps: first generating an image conditioned on the text, and then …
generation into two steps: first generating an image conditioned on the text, and then …
Emu edit: Precise image editing via recognition and generation tasks
Instruction-based image editing holds immense potential for a variety of applications as it
enables users to perform any editing operation using a natural language instruction …
enables users to perform any editing operation using a natural language instruction …
Diffusion model alignment using direct preference optimization
Large language models (LLMs) are fine-tuned using human comparison data with
Reinforcement Learning from Human Feedback (RLHF) methods to make them better …
Reinforcement Learning from Human Feedback (RLHF) methods to make them better …