Related papers: V2V: Scaling Event-Based Vision through Efficient …
Text-to-video generation has advanced rapidly, but existing methods typically output only the final composited video and lack editable layered representations, limiting their use in professional workflows. We propose \textbf{LayerT2V}, a…
This paper introduces V$^2$Edit, a novel training-free framework for instruction-guided video and 3D scene editing. Addressing the critical challenge of balancing original content preservation with editing task fulfillment, our approach…
Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since video content is highly redundant, we argue that naively…
In modern visual SLAM systems, it is a standard practice to retrieve potential candidate map points from overlapping keyframes for further feature matching or direct tracking. In this work, we argue that keyframes are not the optimal choice…
Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that compresses…
Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like…
With the growth of high-quality data and advancement in visual pre-training paradigms, Video Foundation Models (VFMs) have made significant progress recently, demonstrating their remarkable performance on traditional video understanding…
Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve…
Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale…
Event cameras offer microsecond latency, high dynamic range, and low power consumption, making them ideal for real-time robotic perception under challenging conditions such as motion blur, occlusion, and illumination changes. However,…
The event-based Vision-Language Model (VLM) recently has made good progress for practical vision tasks. However, most of these works just utilize CLIP for focusing on traditional perception tasks, which obstruct model understanding…
Vehicle-to-Everything (V2X) collaborative perception extends sensing beyond single vehicle limits through transmission. However, as more agents participate, existing frameworks face two key challenges: (1) the participating agents are…
The event camera, renowned for its high dynamic range and exceptional temporal resolution, is recognized as an important sensor for visual odometry. However, the inherent noise in event streams complicates the selection of high-quality map…
Event cameras sense intensity changes and have many advantages over conventional cameras. To take advantage of event cameras, some methods have been proposed to reconstruct intensity images from event streams. However, the outputs are still…
Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…
Vision-language (VL) learning requires extensive visual perception capabilities, such as fine-grained object recognition and spatial perception. Recent works typically rely on training huge models on massive datasets to develop these…
Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet they remain constrained by scarce annotated real-world V2X driving datasets and limited…
We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from…
Inspired by the success of the text-to-image (T2I) generation task, many researchers are devoting themselves to the text-to-video (T2V) generation task. Most of the T2V frameworks usually inherit from the T2I model and add extra-temporal…
In recent decades, visual simultaneous localization and mapping (vSLAM) has gained significant interest in both academia and industry. It estimates camera motion and reconstructs the environment concurrently using visual sensors on a moving…