Related papers: STREAM: Spatio-TempoRal Evaluation and Analysis Me…
Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider…
Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…
Significant advancements have been made in video generative models recently. Unlike image generation, video generation presents greater challenges, requiring not only generating high-quality frames but also ensuring temporal consistency…
The Fr\'echet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectiveness relies on critical assumptions. Our analysis reveals three significant limitations: (1) the…
While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration…
Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and…
A current limitation of video generative video models is that they generate plausible looking frames, but poor motion -- an issue that is not well captured by FVD and other popular methods for evaluating generated videos. Here we go beyond…
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…
Recently, great progress has been achieved in text-to-video (T2V) generation by scaling transformer-based diffusion models to billions of parameters, which can generate high-quality videos. However, existing models typically produce only…
Frame sampling is a fundamental component in video understanding and video--language model pipelines, yet evaluating the quality of sampled frames remains challenging. Existing evaluation metrics primarily focus on perceptual quality or…
Streaming free-viewpoint video~(FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting~(3DGS), recent 3DGS-based FVV…
Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet satisfying editing results. We attribute this limitation to the prevalent data-to-data…
This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings,…
Fr\'echet Video Distance (FVD), a prominent metric for evaluating video generation models, is known to conflict with human perception occasionally. In this paper, we aim to explore the extent of FVD's bias toward per-frame quality over…
Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits…
The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods…
Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. The inherent ambiguity introduced by occlusions directly violates the brightness constancy constraint and considerably hinders…
Generative models have been widely applied to world modeling for environment simulation and future state prediction. With advancements in autonomous driving, there is a growing demand not only for high-fidelity video generation under…
Generative models have demonstrated remarkable capability in synthesizing high-quality text, images, and videos. For video generation, contemporary text-to-video models exhibit impressive capabilities, crafting visually stunning videos.…
A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propose FlashDepth, a method that satisfies all three…