Neural graphics primitives (NGP) are promising in enabling the smooth integration of old and new assets across various applications. They represent images, shapes, volumetric and spatial-directional data, aiding in novel view synthesis (NeRFs), generative modeling, light caching, and various other applications. Notably successful are the primitives representing data through a feature grid containing trained latent…

Object segmentation across images and videos is a complex yet pivotal task. Traditionally, this field has witnessed a siloed progression, with different tasks such as referring image segmentation (RIS), few-shot image segmentation (FSS), referring video object segmentation (RVOS), and video object segmentation (VOS) evolving independently. This disjointed development resulted in inefficiencies and an inability to…

The development of multimodal large language models (MLLMs) represents a significant leap forward. These advanced systems, which integrate language and visual processing, have broad applications, from image captioning to visible question answering. However, a major challenge has been the high computational resources these models typically require. Existing models, while powerful, necessitate substantial resources for training…

The conventional NeRF and its variations demand considerable computational resources, often surpassing the typical availability in constrained settings. Additionally, client devices’ limited video memory capacity imposes significant constraints on processing and rendering extensive assets concurrently in real-time. The considerable demand for resources poses a crucial challenge in rendering expansive scenes in real-time, requiring rapid loading…

Integrating multimodal data such as text, images, audio, and video is a burgeoning field in AI, propelling advancements far beyond traditional single-mode models. Traditional AI has thrived in unimodal contexts, yet the complexity of real-world data often intertwines these modes, presenting a substantial challenge. This complexity demands a model capable of processing and seamlessly integrating…

Physics-based character animation, a field at the intersection of computer graphics and physics, aims to create lifelike, responsive character movements. This domain has long been a bedrock of digital animation, seeking to replicate the complexities of real-world motion in a virtual environment. The challenge lies in the technical aspects of animation and in capturing the…

Text-to-image generation has evolved significantly, a fascinating intersection of artificial intelligence and creativity. This technology, which transforms textual descriptions into visual content, has broad applications ranging from artistic endeavors to educational tools. Its capability to produce detailed images from text inputs marks a substantial leap in digital content creation, offering a blend of technology and…

The captivating domain of 3D animation and modeling, which encompasses creating lifelike three-dimensional representations of objects and living beings, has long intrigued scientific and artistic communities. This area, crucial for advancements in computer vision and mixed reality applications, has provided unique insights into the dynamics of physical movements in a digital realm. A prominent challenge…

Artificial intelligence has recently been used in all spheres of life. Likewise, it is being used for video generation and video editing. AI has opened up new possibilities for creativity, enabling seamless content generation and manipulation. However, video editing remains challenging due to the intricate nature of maintaining temporal coherence between individual frames. The Traditional…

The seamless integration of vision and language has been a focal point of recent advancements in AI. The field has seen significant progress with the advent of LLMs. Yet, developing vision and vision-language foundation models essential for multimodal AGI systems still need to catch up. This gap has led to the creation of a groundbreaking…