Score distillation sampling (SDS) has shown great promise in text-to-3D generation by
distilling pretrained large-scale text-to-image diffusion models, but suffers from over …

We propose a method for editing NeRF scenes with text-instructions. Given a NeRF of a
scene and the collection of images used to reconstruct it, our method uses an image …

Finding correspondences between images is a fundamental problem in computer vision. In
this paper, we show that correspondence emerges in image diffusion models without any …

Automatic text-to-3D generation that combines Score Distillation Sampling (SDS) with the
optimization of volume rendering has achieved remarkable progress in synthesizing realistic …

Recently, diffusion models have achieved remarkable success in text-to-image generation,
enabling the creation of high-quality images from text prompts and various conditions …

Deep learning models are often trained on distributed, web-scale datasets crawled from the
internet. In this paper, we introduce two new dataset poisoning attacks that intentionally …

Diffusion models are powerful, but they require a lot of time and data to train. We propose
Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training …

Diffusion models excel at text-to-image generation, especially in subject-driven generation
for personalized images. However, existing methods are inefficient due to the subject …

The artistic style within a painting is the means of expression, which includes not only the
painting material, colors, and brushstrokes, but also the high-level attributes, including …

Diffusion models have shown remarkable success in visual synthesis, but have also raised
concerns about potential abuse for malicious purposes. In this paper, we seek to build a …