Related papers: E$^3$C: Video Generation with 3D Environmental Mem…

We propose a method for object-aware 3D egocentric pose estimation that tightly integrates kinematics modeling, dynamics modeling, and scene object information. Unlike prior kinematics or dynamics-based approaches where the two components…

High-quality driving video generation is crucial for providing training data for autonomous driving models. However, current generative models rarely focus on enhancing camera motion control under multi-view tasks, which is essential for…

We present En3D, an enhanced generative scheme for sculpting high-quality 3D human avatars. Unlike previous works that rely on scarce 3D datasets or limited 2D collections with imbalanced viewing angles and imprecise pose priors, our…

Can conversational videos captured from multiple egocentric viewpoints reveal the map of a scene in a cost-efficient way? We seek to answer this question by proposing a new problem: efficiently building the map of a previously unseen 3D…

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to…

We propose the use of a proportional-derivative (PD) control based policy learned via reinforcement learning (RL) to estimate and forecast 3D human pose from egocentric videos. The method learns directly from unsegmented egocentric videos…

A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird's-eye-view (BEV) coordinate frame of the ego car in order to ground downstream planner. Existing perception methods…

Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. A major issue in such scenarios for real-world applications is that may easily become necessary…

Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this…

We present EMBED (Egocentric Models Built with Exocentric Data), a method designed to transform exocentric video-language data for egocentric video representation learning. Large-scale exocentric data covers diverse activities with…

Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocentric interaction in AR/VR, telepresence, and hand-centric manipulation tasks, where…

Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), attribute-induced…

Photorealistic 3D scene generation is challenging due to the scarcity of large-scale, high-quality real-world 3D datasets and complex workflows requiring specialized expertise for manual modeling. These constraints often result in slow…

Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability…

In this paper, we present Export3D, a one-shot 3D-aware portrait animation method that is able to control the facial expression and camera view of a given portrait image. To achieve this, we introduce a tri-plane generator with an effective…

We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, our model has precise control over object dynamics, ego-agent…

As the demand for analyzing egocentric videos grows, egocentric visual attention prediction, anticipating where a camera wearer will attend, has garnered increasing attention. However, it remains challenging due to the inherent complexity…

Human video generation is a dynamic and rapidly evolving task that aims to synthesize 2D human body video sequences with generative models given control conditions such as text, audio, and pose. With the potential for wide-ranging…

Event cameras offer multiple advantages in monocular egocentric 3D human pose estimation from head-mounted devices, such as millisecond temporal resolution, high dynamic range, and negligible motion blur. Existing methods effectively…

First-person video naturally brings the use of a physical environment to the forefront, since it shows the camera wearer interacting fluidly in a space based on his intentions. However, current methods largely separate the observed actions…