Related papers: GASP: Unifying Geometric and Semantic Self-Supervi…
3D semantic occupancy prediction is crucial for autonomous driving. While multi-modal fusion improves accuracy over vision-only methods, it typically relies on computationally expensive dense voxel or BEV tensors. We present Gau-Occ, a…
3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, its effectiveness is inherently constrained in…
What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: the geometric structure of the physical world. Training a VAE-based world model on random…
As an essential task in autonomous driving (AD), motion prediction aims to predict the future states of surround objects for navigation. One natural solution is to estimate the position of other agents in a step-by-step manner where each…
Most invariance-based self-supervised methods rely on single object-centric images (e.g., ImageNet images) for pretraining, learning features that invariant to geometric transformation. However, when images are not object-centric, the…
Medical images are naturally associated with rich semantics about the human anatomy, reflected in an abundance of recurring anatomical patterns, offering unique potential to foster deep semantic representation learning and yield…
Designing agents, capable of learning autonomously a wide range of skills is critical in order to increase the scope of reinforcement learning. It will both increase the diversity of learned skills and reduce the burden of manually…
Understanding world dynamics is crucial for planning in autonomous driving. Recent methods attempt to achieve this by learning a 3D occupancy world model that forecasts future surrounding scenes based on current observation. However, 3D…
Foundation models have transformed vision and language by learning general-purpose representations from large-scale unlabeled data, yet 3D medical imaging lacks analogous approaches. Existing self-supervised methods rely on low-level…
Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts…
In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…
A semantic map of the road scene, covering fundamental road elements, is an essential ingredient in autonomous driving systems. It provides important perception foundations for positioning and planning when rendered in the Bird's-Eye-View…
Generative models have shown promising results in capturing human mobility characteristics and generating synthetic trajectories. However, it remains challenging to ensure that the generated geospatial mobility data is semantically…
Grasping in cluttered scenes has always been a great challenge for robots, due to the requirement of the ability to well understand the scene and object information. Previous works usually assume that the geometry information of the objects…
We integrate two powerful ideas, geometry and deep visual representation learning, into recurrent network architectures for mobile visual scene understanding. The proposed networks learn to "lift" and integrate 2D visual features over time…
Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured latent space such as visual keypoints often outperforms…
Self-supervised representation learning techniques utilize large datasets without semantic annotations to learn meaningful, universal features that can be conveniently transferred to solve a wide variety of downstream supervised tasks. In…
Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have shown great promise…
Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin…
Accurate perception of the surrounding environment is essential for safe autonomous driving. 3D occupancy prediction, which estimates detailed 3D structures of roads, buildings, and other objects, is particularly important for…