相关论文: SkyReels-V3 Technique Report

Modern video codecs and learning-based approaches struggle for semantic reconstruction at extremely low bit-rates due to reliance on low-level spatiotemporal redundancies. Generative models, especially diffusion models, offer a new paradigm…

With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing…

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial…

Storytelling video generation (SVG) aims to produce coherent and visually rich multi-scene videos that follow a structured narrative. Existing methods primarily employ LLM for high-level planning to decompose a story into scene-level…

Despite significant advances in video synthesis, research into multi-shot video generation remains in its infancy. Even with scaled-up models and massive datasets, the shot transition capabilities remain rudimentary and unstable, largely…

Text-to-video generation is an emerging field in generative AI, enabling the creation of realistic, semantically accurate videos from text prompts. While current models achieve impressive visual quality and alignment with input text, they…

We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag…

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…

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…

Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual…

We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual embeddings via learnable query tokens, which subsequently…

Recent years have witnessed remarkable progress in multi-view diffusion models for 3D content creation. However, there remains a significant gap in image quality and prompt-following ability compared to 2D diffusion models. A critical…

State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In this paper, we argue that many errors,…

Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generalizable 3D world generation. However, existing approaches often…

Despite substantial progress in text-to-video generation, achieving precise and flexible control over fine-grained spatiotemporal attributes remains a significant unresolved challenge in video generation research. To address these…

We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis either…

Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities…

Video Diffusion Models (VDMs) have emerged as powerful generative tools, capable of synthesizing high-quality spatiotemporal content. Yet, their potential goes far beyond mere video generation. We argue that the training dynamics of VDMs,…

Leveraging text, images, structure maps, or motion trajectories as conditional guidance, diffusion models have achieved great success in automated and high-quality video generation. However, generating smooth and rational transition videos…