Related papers: Auto-CARD: Efficient and Robust Codec Avatar Drivi…
Over the last few years, neural image compression has gained wide attention from research and industry, yielding promising end-to-end deep neural codecs outperforming their conventional counterparts in rate-distortion performance. Despite…
Radars and cameras are mature, cost-effective, and robust sensors and have been widely used in the perception stack of mass-produced autonomous driving systems. Due to their complementary properties, outputs from radar detection (radar…
3D rendering of dynamic face captures is a challenging problem, and it demands improvements on several fronts$\unicode{x2014}$photorealism, efficiency, compatibility, and configurability. We present a novel representation that enables…
Creating realistic virtual assets is a time-consuming process: it usually involves an artist designing the object, then spending a lot of effort on tweaking its appearance. Intricate details and certain effects, such as subsurface…
Designing suitable deep model architectures, for AI-driven on-device apps and features, at par with rapidly evolving mobile hardware and increasingly complex target scenarios is a difficult task. Though Neural Architecture Search…
We present a novel system for real-time tracking of facial expressions using egocentric views captured from a set of infrared cameras embedded in a virtual reality (VR) headset. Our technology facilitates any user to accurately drive the…
Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely…
Autonomous vehicles (AVs) are rapidly evolving as an innovative mode of transportation. However, the consensus in both industry and academia is that AVs cannot independently resolve all traffic scenarios. Consequently, the need for remote…
Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability. Deep neural networks for video tasks is highly customized and the design of such networks requires domain experts and…
Vision-Language-Action (VLA) models have demonstrated strong multi-modal reasoning capabilities, enabling direct action generation from visual perception and language instructions in an end-to-end manner. However, their substantial…
Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications. Compared…
This study explores a streamlined facial data collection method for conversational contexts, addressing the limitations of existing approaches that often require extensive datasets and prioritize technical metrics over user perception and…
In a voice-controlled smart-home, a controller must respond not only to user's requests but also according to the interaction context. This paper describes Arcades, a system which uses deep reinforcement learning to extract context from a…
Traditional lecture videos offer flexibility but lack mechanisms for real-time clarification, forcing learners to search externally when confusion arises. Recent advances in large language models and neural avatars provide new opportunities…
Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt,…
We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) Vision-and-Language navigation challenge of Anderson et. al.…
Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the…
One of the main paths towards the reduction of traffic accidents is the increase in vehicle safety through driver assistance systems or even systems with a complete level of autonomy. In these types of systems, tasks such as obstacle…
Synthesizing photorealistic 4D human head avatars from videos is essential for VR/AR, telepresence, and video game applications. Although existing Neural Radiance Fields (NeRF)-based methods achieve high-fidelity results, the computational…
Despite recent progress in developing animatable full-body avatars, realistic modeling of clothing - one of the core aspects of human self-expression - remains an open challenge. State-of-the-art physical simulation methods can generate…