Related papers: Tiger200K: Manually Curated High Visual Quality Vi…

Unconditional human image generation is an important task in vision and graphics, which enables various applications in the creative industry. Existing studies in this field mainly focus on "network engineering" such as designing new…

Recent advances in multimodal models have demonstrated remarkable text-guided image editing capabilities, with systems like GPT-4o and Nano-Banana setting new benchmarks. However, the research community's progress remains constrained by the…

Diffusion based video generation has received extensive attention and achieved considerable success within both the academic and industrial communities. However, current efforts are mainly concentrated on single-objective or single-task…

Many recent advances in robotic manipulation have come through imitation learning, yet these rely largely on mimicking a particularly hard-to-acquire form of demonstrations: those collected on the same robot in the same room with the same…

Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D text-to-image diffusion models into the 3D domain for…

In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…

Data availability is crucial for advancing artificial intelligence applications, including voice-based technologies. As content creation, particularly in social media, experiences increasing demand, translation and text-to-speech (TTS)…

We present a novel approach for generating 360-degree high-quality, spatio-temporally coherent human videos from a single image. Our framework combines the strengths of diffusion transformers for capturing global correlations across…

Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three…

AI-based image enhancement techniques have been widely adopted in various visual applications, significantly improving the perceptual quality of user-generated content (UGC). However, the lack of specialized quality assessment models has…

Controllable image captioning models generate human-like image descriptions, enabling some kind of control over the generated captions. This paper focuses on controlling the caption length, i.e. a short and concise description or a long and…

Large-scale video repositories are increasingly available for modern video understanding and generation tasks. However, transforming raw videos into high-quality, task-specific datasets remains costly and inefficient. We present DataCube,…

OpenKinoAI is an open source framework for post-production of ultra high definition video which makes it possible to emulate professional multiclip editing techniques for the case of single camera recordings. OpenKinoAI includes tools for…

Existing automated dubbing methods are usually designed for Professionally Generated Content (PGC) production, which requires massive training data and training time to learn a person-specific audio-video mapping. In this paper, we…

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and…

Video generation models have developed rapidly in recent years, where generating natural human motion plays a pivotal role. However, accurately evaluating the quality of generated human motion video remains a significant challenge. Existing…

High-quality video generation, encompassing text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation, holds considerable significance in content creation to benefit anyone express their inherent creativity in new ways…

In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, both for data storage and model training. Dataset distillation…

While text-to-video diffusion models have advanced significantly, creating coherent long-form content remains unreliable due to stochastic sampling artifacts. This necessitates generating multiple candidates, yet verifying them creates a…

In this work, we systematically study the problem of personalized text-to-image generation, where the output image is expected to portray information about specific human subjects. E.g., generating images of oneself appearing at imaginative…