Search Results for author:
Found 10 papers, 4 papers with code
AnyV2V: A Plug-and-Play Framework For Any Video-to-Video Editing Tasks
In the second stage, AnyV2V can plug in any existing image-to-video models to perform DDIM inversion and intermediate feature injection to maintain the appearance and motion consistency with the source video.
ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation
To verify the effectiveness of our method, we propose I2V-Bench, a comprehensive evaluation benchmark for I2V generation.
Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation
In contrast, we propose a parameter-free temporal shift module that can leverage the spatial U-Net as is for video generation.
Make-A-Video: Text-to-Video Generation without Text-Video Data
We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V).
Ranked #3 on
Text-to-Video Generation
on MSR-VTT
(CLIP-FID metric)
RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness
We show that the effectiveness of the well celebrated Mixup [Zhang et al., 2018] can be further improved if instead of using it as the sole learning objective, it is utilized as an additional regularizer to the standard cross-entropy loss.
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Videos are created to express emotion, exchange information, and share experiences.
Ranked #15 on
Video Generation
on UCF-101
Mix-MaxEnt: Creating High Entropy Barriers To Improve Accuracy and Uncertainty Estimates of Deterministic Neural Networks
We propose an extremely simple approach to regularize a single deterministic neural network to obtain improved accuracy and reliable uncertainty estimates.
Robustness and Generalization via Generative Adversarial Training
Adversarial training with these examples enable the model to withstand a wide range of attacks by observing a variety of input alterations during training.
Fine-grained Synthesis of Unrestricted Adversarial Examples
We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation.
