Related papers: Towards Physically Consistent 4D Scene Reconstruct…
Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead to suboptimal…
This paper aims to tackle the problem of modeling dynamic urban streets for autonomous driving scenes. Recent methods extend NeRF by incorporating tracked vehicle poses to animate vehicles, enabling photo-realistic view synthesis of dynamic…
Modern 3D semantic scene graph estimation methods utilize ground truth 3D annotations to accurately predict target objects, predicates, and relationships. In the absence of given 3D ground truth representations, we explore leveraging only…
Novel view synthesis of dynamic scenes is fundamental to achieving photorealistic 4D reconstruction and immersive visual experiences. Recent progress in Gaussian-based representations has significantly improved real-time rendering quality,…
Recent advances in 3D scene representations have enabled high-fidelity novel view synthesis, yet adapting to discrete scene changes and constructing interactive 3D environments remain open challenges in vision and robotics. Existing…
Novel view synthesis has demonstrated impressive progress recently, with 3D Gaussian splatting (3DGS) offering efficient training time and photorealistic real-time rendering. However, reliance on Cartesian coordinates limits 3DGS's…
This work focuses on modeling dynamic urban environments for autonomous driving simulation. Contemporary data-driven methods using neural radiance fields have achieved photorealistic driving scene modeling, but they suffer from low…
Open-vocabulary 3D scene understanding is crucial for applications requiring natural language-driven spatial interpretation, such as robotics and augmented reality. While 3D Gaussian Splatting (3DGS) offers a powerful representation for…
Recently, 3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it encounters challenges for high-resolution novel view synthesis (HRNVS) due to the…
In the realm of robot-assisted minimally invasive surgery, dynamic scene reconstruction can significantly enhance downstream tasks and improve surgical outcomes. Neural Radiance Fields (NeRF)-based methods have recently risen to prominence…
Synthesis of diverse driving scenes serves as a crucial data augmentation technique for validating the robustness and generalizability of autonomous driving systems. Current methods aggregate high-definition (HD) maps and 3D bounding boxes…
Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification problem rather…
Open-vocabulary scene understanding is crucial for robotic applications, enabling robots to comprehend complex 3D environmental contexts and supporting various downstream tasks such as navigation and manipulation. However, existing methods…
The scene perception, understanding, and simulation are fundamental techniques for embodied-AI agents, while existing solutions are still prone to segmentation deficiency, dynamic objects' interference, sensor data sparsity, and…
Reconstructing and predicting dynamic 3D scenes from multi-view videos is a foundational task for robotics, AR/VR, and digital twins. Recent physics-informed Gaussian Splatting methods achieve impressive future frame extrapolation but lack…
Safety-critical scenarios are essential for training and evaluating autonomous driving (AD) systems, yet remain extremely rare in real-world driving datasets. To address this, we propose Real-world Crash Grounding (RCG), a scenario…
Viewpoint missing of objects is common in scene reconstruction, as camera paths typically prioritize capturing the overall scene structure rather than individual objects. This makes it highly challenging to achieve high-fidelity…
Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…
Dynamic scenes rendering is an intriguing yet challenging problem. Although current methods based on NeRF have achieved satisfactory performance, they still can not reach real-time levels. Recently, 3D Gaussian Splatting (3DGS) has garnered…
Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no…