Related papers: 4D LangSplat: 4D Language Gaussian Splatting via M…
Egocentric scenes exhibit frequent occlusions, varied viewpoints, and dynamic interactions compared to typical scene understanding tasks. Occlusions and varied viewpoints can lead to multi-view semantic inconsistencies, while dynamic…
Understanding dynamic 4D environments through natural language queries requires not only accurate scene reconstruction but also robust semantic grounding across space, time, and viewpoints. While recent methods using neural representations…
To enable AI agents to interact seamlessly with both humans and 3D environments, they must not only perceive the 3D world accurately but also align human language with 3D spatial representations. While prior work has made significant…
Realistic reconstruction of dynamic 4D scenes from monocular videos is essential for understanding the physical world. Despite recent progress in neural rendering, existing methods often struggle to recover accurate 3D geometry and…
Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily…
Capturing 4D spatiotemporal surroundings is crucial for the safe and reliable operation of robots in dynamic environments. However, most existing methods address only one side of the problem: they either provide coarse geometric tracking…
Language-guided 3D scene understanding is important for advancing applications in robotics, AR/VR, and human-computer interaction, enabling models to comprehend and interact with 3D environments through natural language. While 2D…
Previous text-to-4D methods have leveraged multiple Score Distillation Sampling (SDS) techniques, combining motion priors from video-based diffusion models (DMs) with geometric priors from multiview DMs to implicitly guide 4D renderings.…
Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic environments and enable open-vocabulary querying in complex…
LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift,…
Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also…
In robot-assisted minimally invasive surgery, high-fidelity dynamic endoscopic scene reconstruction and simulation are crucial to enhancing downstream tasks and advancing surgical outcomes. However, existing methods primarily focus on…
Modeling dynamic scenes through 4D Gaussians offers high visual fidelity and fast rendering speeds, but comes with significant storage overhead. Recent approaches mitigate this cost by aggressively reducing the number of Gaussians. However,…
Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D…
We introduce Dr. Splat, a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Unlike existing language-embedded 3DGS methods, which rely on a rendering process, our method directly associates…
Language-augmented scene representations hold great promise for large-scale robotics applications such as search-and-rescue, smart cities, and mining. Many of these scenarios are time-sensitive, requiring rapid scene encoding while also…
3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction, offering high-quality novel view synthesis while maintaining computational efficiency. In this paper, we extend the capabilities of 3DGS…
Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling…
3D Gaussian Splatting (3DGS) has garnered significant attention due to its superior scene representation fidelity and real-time rendering performance, especially for dynamic 3D scene reconstruction (\textit{i.e.}, 4D reconstruction).…
Language-driven 3D Gaussian Splatting (3DGS) editing provides a more convenient approach for modifying complex scenes in VR/AR. Standard pipelines typically adopt a two-stage strategy: first editing multiple 2D views, and then optimizing…