Related papers: FlowDreamer: A RGB-D World Model with Flow-based M…
The use of deep learning methods for modeling fluid flow has drawn a lot of attention in the past few years. In situations where conventional numerical approaches can be computationally expensive, these techniques have shown promise in…
Point clouds are a widely available and canonical data modality which convey the 3D geometry of a scene. Despite significant progress in classification and segmentation from point clouds, policy learning from such a modality remains…
Drag-based editing allows precise object manipulation through point-based control, offering user convenience. However, current methods often suffer from a geometric inconsistency problem by focusing exclusively on matching user-defined…
Recent work on visual representation learning has shown to be efficient for robotic manipulation tasks. However, most existing works pretrained the visual backbone solely on 2D images or egocentric videos, ignoring the fact that robots…
For a robot to act intelligently, it needs to sense the world around it. Increasingly, robots build an internal representation of the world from sensor readings. This representation can then be used to inform downstream tasks, such as…
Learning an accurate model of the environment is essential for model-based control tasks. Existing methods in robotic visuomotor control usually learn from data with heavily labelled actions, object entities or locations, which can be…
A world model is essential for an agent to predict the future and plan in domains such as autonomous driving and robotics. To achieve this, recent advancements have focused on video generation, which has gained significant attention due to…
Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry…
Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their…
World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current embodied world models…
To safely navigate intricate real-world scenarios, autonomous vehicles must be able to adapt to diverse road conditions and anticipate future events. World model (WM) based reinforcement learning (RL) has emerged as a promising approach by…
Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency. However, a systemic challenge remains unresolved, as inherent latency…
The collection of large-scale and diverse robot demonstrations remains a major bottleneck for imitation learning, as real-world data acquisition is costly and simulators offer limited diversity and fidelity with pronounced sim-to-real gaps.…
Video prediction is commonly referred to as forecasting future frames of a video sequence provided several past frames thereof. It remains a challenging domain as visual scenes evolve according to complex underlying dynamics, such as the…
Challenges in traversing dynamic clutters lie mainly in the efficient perception of the environmental dynamics and the generation of evasive behaviors considering obstacle movement. Previous solutions have made progress in explicitly…
When working with 3D facial data, improving fidelity and avoiding the uncanny valley effect is critically dependent on accurate 3D facial performance capture. Because such methods are expensive and due to the widespread availability of 2D…
Predicting future motion trajectories is a critical capability across domains such as robotics, autonomous systems, and human activity forecasting, enabling safer and more intelligent decision-making. This paper proposes a novel, efficient,…
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained…
Recently, the RGB images and point clouds fusion methods have been proposed to jointly estimate 2D optical flow and 3D scene flow. However, as both conventional RGB cameras and LiDAR sensors adopt a frame-based data acquisition mechanism,…
The field of autonomous driving is experiencing a surge of interest in world models, which aim to predict potential future scenarios based on historical observations. In this paper, we introduce DFIT-OccWorld, an efficient 3D occupancy…