相关论文: Scaling Zero-Shot Reference-to-Video Generation

Videos show continuous events, yet most $-$ if not all $-$ video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be $-$ time-continuous signals, and extend the paradigm of neural…

Many recent methods of zero-shot learning (ZSL) attempt to utilize generative model to generate the unseen visual samples from semantic descriptions and random noise. Therefore, the ZSL problem becomes a traditional supervised…

Text-image-to-video (TI2V) generation is a critical problem for controllable video generation using both semantic and visual conditions. Most existing methods typically add visual conditions to text-to-video (T2V) foundation models by…

We introduce the first zero-shot approach for Video Semantic Segmentation (VSS) based on pre-trained diffusion models. A growing research direction attempts to employ diffusion models to perform downstream vision tasks by exploiting their…

Composed Image Retrieval (CIR) is a task that retrieves images similar to a query, based on a provided textual modification. Current techniques rely on supervised learning for CIR models using labeled triplets of the reference image, text,…

Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should learn to associate components in the sketch (say, feet, tail,…

Scene understanding and reasoning has been a fundamental problem in 3D computer vision, requiring models to identify objects, their properties, and spatial or comparative relationships among the objects. Existing approaches enable this by…

We present RefVFX, a new framework that transfers complex temporal effects from a reference video onto a target video or image in a feed-forward manner. While existing methods excel at prompt-based or keyframe-conditioned editing, they…

Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts. Recent methods have tried to replicate the success by either training text-to-video (T2V) models on a…

Most text-to-video(T2V) diffusion models depend on pre-trained text encoders for semantic alignment, yet they often fail to maintain video quality when provided with concise prompts rather than well-designed ones. The primary issue lies in…

Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…

We propose SALSA-V, a multimodal video-to-audio generation model capable of synthesizing highly synchronized, high-fidelity long-form audio from silent video content. Our approach introduces a masked diffusion objective, enabling…

Both zero-shot and tuning-based customized text-to-image (CT2I) generation have made significant progress for storytelling content creation. In contrast, research on customized text-to-video (CT2V) generation remains relatively limited.…

Recent methods for single image super-resolution (SISR) have demonstrated outstanding performance in generating high-resolution (HR) images from low-resolution (LR) images. However, most of these methods show their superiority using…

Customized generation has achieved significant progress in image synthesis, yet personalized video generation remains challenging due to temporal inconsistencies and quality degradation. In this paper, we introduce CustomVideoX, an…

Zero-shot learning (ZSL) aims to recognize classes that do not have samples in the training set. One representative solution is to directly learn an embedding function associating visual features with corresponding class semantics for…

Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS…

Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial distribution of objects, environment and agent itself. To…

Referring video object segmentation (RVOS) aims to segment the target instance in a video, referred by a text expression. Conventional approaches are mostly supervised learning, requiring expensive pixel-level mask annotations. To tackle…

Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the…