most citedLightSpeed: Light and Fast Neural Light Fields on Mobile Devices

2 citations · 2 across the 7 of their papers we have counts for

collaborators

11 papers

cs.CV2024

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

Dongting Hu, Jierun Chen, Xijie Huang +16

Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…

cs.CV2024

Wonderland: Navigating 3D Scenes from a Single Image

Hanwen Liang, Junli Cao, Vidit Goel +6

How can one efficiently generate high-quality, wide-scope 3D scenes from arbitrary single images? Existing methods suffer several drawbacks, such as requiring multi-view data, time…

cs.CV2024

Efficient Training with Denoised Neural Weights

Yifan Gong, Zheng Zhan, Yanyu Li +6

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challengin…

cs.CV2024

TextCraftor: Your Text Encoder Can be Image Quality Controller

Yanyu Li, Xian Liu, Anil Kag +6

Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation, enabling significant advancements in areas like image…

cs.CV2024

SPAD : Spatially Aware Multiview Diffusers

Yash Kant, Ziyi Wu, Michael Vasilkovsky +7

We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation, we repurpose a pretrained 2D diffus…

cs.CV2024

Visual Concept-driven Image Generation with Text-to-Image Diffusion Model

Tanzila Rahman, Shweta Mahajan, Hsin-Ying Lee +3

Text-to-image (TTI) diffusion models have demonstrated impressive results in generating high-resolution images of complex and imaginative scenes. Recent approaches have further ext…