Related papers: PanopticQuery: Unified Query-Time Reasoning for 4D…
Latent scene representation plays a significant role in training reinforcement learning (RL) agents. To obtain good latent vectors describing the scenes, recent works incorporate the 3D-aware latent-conditioned NeRF pipeline into scene…
Dynamic scene rendering has taken a leap forward with the rise of 4D Gaussian Splatting, but there's still one elusive challenge: how to make 3D Gaussians move through time as naturally as they would in the real world, all while keeping the…
4D Gaussian Splatting (4DGS) has recently gained considerable attention as a method for reconstructing dynamic scenes. Despite achieving superior quality, 4DGS typically requires substantial storage and suffers from slow rendering speed. In…
Editing 4D scenes reconstructed from monocular videos based on text prompts is a valuable yet challenging task with broad applications in content creation and virtual environments. The key difficulty lies in achieving semantically precise…
Gaussian Splatting has been considered as a novel way for view synthesis of dynamic scenes, which shows great potential in AIoT applications such as digital twins. However, recent dynamic Gaussian Splatting methods significantly degrade…
Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality.…
Modeling 3D language fields with Gaussian Splatting for open-ended language queries has recently garnered increasing attention. However, recent 3DGS-based models leverage view-dependent 2D foundation models to refine 3D semantics but lack a…
Recent advancements in 3D Gaussian Splatting(3DGS) have significantly improved semantic scene understanding, enabling natural language queries to localize objects within a scene. However, existing methods primarily focus on embedding…
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…
Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments by linking geometry with descriptive meaning. This allows for a more intuitive human-computer interaction, enabling querying or…
We investigate a challenging task of dynamic scene geometry estimation, which requires representing both spatial and temporal features. Typically, existing methods align the two features into a unified latent space to model scene geometry.…
This paper introduces a novel method for open-vocabulary 3D scene querying in autonomous driving by combining Language Embedded 3D Gaussians with Large Language Models (LLMs). We propose utilizing LLMs to generate both contextually…
Existing 3D scene generation methods often struggle to model the complex logical dependencies and physical constraints between objects, limiting their ability to adapt to dynamic and realistic environments. We propose CausalStruct, a novel…
3D Gaussian Splatting (GS) enables fast and high-quality scene reconstruction, but it lacks an object-consistent and semantically aware structure. We propose Split&Splat, a framework for panoptic scene reconstruction using 3DGS. Our…
Comprehensive modeling of the surrounding 3D world is key to the success of autonomous driving. However, existing perception tasks like object detection, road structure segmentation, depth & elevation estimation, and open-set object…
We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image. Our approach unifies the generative priors of video diffusion models with geometry and motion constraints learned from…
For robotic interaction in environments shared with other agents, access to volumetric and semantic maps of the scene is crucial. However, such environments are inevitably subject to long-term changes, which the map needs to account for. We…
For vision-language models (VLMs), understanding the dynamic properties of objects and their interactions in 3D scenes from videos is crucial for effective reasoning about high-level temporal and action semantics. Although humans are adept…
With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to…
Humans inhabit a physical 4D world where geometric structure and semantic content evolve over time, constituting a dynamic 4D reality (spatial with temporal dimension). While current Multimodal Large Language Models (MLLMs) excel in static…