Related papers: Manboformer: Learning Gaussian Representations via…
Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While…
Recent developments in 3D reconstruction and neural rendering have significantly propelled the capabilities of photo-realistic 3D scene rendering across various academic and industrial fields. The 3D Gaussian Splatting technique, alongside…
Accurate and realistic 3D scene reconstruction enables the lifelike creation of autonomous driving simulation environments. With advancements in 3D Gaussian Splatting (3DGS), previous studies have applied it to reconstruct complex dynamic…
We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…
3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…
Recently, 3D Gaussian Spatting (3DGS) has gained widespread attention in Novel View Synthesis (NVS) due to the remarkable real-time rendering performance. However, the substantial cost of storage and transmission of vanilla 3DGS hinders its…
3D occupancy prediction enables the robots to obtain spatial fine-grained geometry and semantics of the surrounding scene, and has become an essential task for embodied perception. Existing methods based on 3D Gaussians instead of dense…
A robust awareness of how dynamic scenes evolve is essential for Autonomous Driving systems, as they must accurately detect, track, and predict the behaviour of surrounding obstacles. Traditional perception pipelines that rely on modular…
In this paper, we propose to employ a Gaussian map representation to estimate precise location and count of 3D surface features, addressing the limitations of state-of-the-art methods based on density estimation which struggle in presence…
Semantic reconstruction of agricultural scenes plays a vital role in tasks such as phenotyping and yield estimation. However, traditional approaches that rely on manual scanning or fixed camera setups remain a major bottleneck in this…
World models for autonomous driving have the potential to dramatically improve the reasoning capabilities of today's systems. However, most works focus on camera data, with only a few that leverage lidar data or combine both to better…
Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we argue that the existing attention mechanism faces the problem…
Scene understanding is crucial for autonomous robots in dynamic environments for making future state predictions, avoiding collisions, and path planning. Camera and LiDAR perception made tremendous progress in recent years, but face…
In this paper, we introduce a non-parametric memory representation for spatio-temporal segmentation that captures the local space and time around an autonomous vehicle (AV). Our representation has three important properties: (i) it…
As the most representative scenario of spatial-temporal forecasting tasks, the traffic forecasting task attracted numerous attention from machine learning community due to its intricate correlation both in space and time dimension. Existing…
Low-level 3D representations, such as point clouds, meshes, NeRFs and 3D Gaussians, are commonly used for modeling 3D objects and scenes. However, cognitive studies indicate that human perception operates at higher levels and interprets 3D…
Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and…
Reconstructing and understanding 3D scenes from unposed sparse views in a feed-forward manner remains as a challenging task in 3D computer vision. Recent approaches use per-pixel 3D Gaussian Splatting for reconstruction, followed by a…
Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel…
Photorealistic 3D reconstruction of street scenes is a critical technique for developing real-world simulators for autonomous driving. Despite the efficacy of Neural Radiance Fields (NeRF) for driving scenes, 3D Gaussian Splatting (3DGS)…