Related papers: InfVSR: Toward Consistency-Driven Streaming Genera…
High-resolution (HR) medical videos are vital for accurate diagnosis, yet are hard to acquire due to hardware limitations and physiological constraints. Clinically, the collected low-resolution (LR) medical videos present unique challenges…
We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, conventional…
Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view…
By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose…
Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing…
Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…
Infrared and visible video fusion is essential for achieving comprehensive perception in dynamic scenes. However, maintaining temporal consistency remains a formidable challenge. Conventional methods relying on optical flow often suffer…
We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can…
Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly…
Long videos, ranging from minutes to hours, present significant challenges for current Multi-modal Large Language Models (MLLMs) due to their complex events, diverse scenes, and long-range dependencies. Direct encoding of such videos is…
Recovering 3D scenes from sparse views is a challenging task due to its inherent ill-posed problem. Conventional methods have developed specialized solutions (e.g., geometry regularization or feed-forward deterministic model) to mitigate…
Creating high-fidelity, coherent long videos is a sought-after aspiration. While recent video diffusion models have shown promising potential, they still grapple with spatiotemporal inconsistencies and high computational resource demands.…
In this paper, we explore the space-time video super-resolution task, which aims to generate a high-resolution (HR) slow-motion video from a low frame rate (LFR), low-resolution (LR) video. A simple solution is to split it into two…
Diffusion models have achieved remarkable progress in the field of video generation. However, their iterative denoising nature requires a large number of inference steps to generate a video, which is slow and computationally expensive. In…
As a fundamental challenge in visual computing, video super-resolution (VSR) focuses on reconstructing highdefinition video sequences from their degraded lowresolution counterparts. While deep convolutional neural networks have demonstrated…
Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon drift of current diffusion models. We present Live Avatar, an…
Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. When applied to multi-view images, existing single-view approaches often ignore cross-view relationships, leading to…
High-resolution image-to-video (I2V) generation aims to synthesize realistic temporal dynamics while preserving fine-grained appearance details of the input image. At 2K resolution, it becomes extremely challenging, and existing solutions…
Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. To bridge this persistent domain gap, we introduce a large-scale, dynamic…
Understanding and reasoning over long videos pose significant challenges for large video language models (LVLMs) due to the difficulty in processing intensive video tokens beyond context window and retaining long-term sequential…