Related papers: ReferSplat: Referring Segmentation in 3D Gaussian …
Object navigation is a core capability of embodied intelligence, enabling an agent to locate target objects in unknown environments. Recent advances in vision-language models (VLMs) have facilitated zero-shot object navigation (ZSON).…
We introduce Go-SLAM, a novel framework that utilizes 3D Gaussian Splatting SLAM to reconstruct dynamic environments while embedding object-level information within the scene representations. This framework employs advanced object…
Referenced-based scene stylization that edits the appearance based on a content-aligned reference image is an emerging research area. Starting with a pretrained neural radiance field (NeRF), existing methods typically learn a novel…
Multimodal referring segmentation aims to segment target objects in visual scenes, such as images, videos, and 3D scenes, based on referring expressions in text or audio format. This task plays a crucial role in practical applications…
Recognizing arbitrary or previously unseen categories is essential for comprehensive real-world 3D scene understanding. Currently, all existing methods rely on 2D or textual modalities during training or together at inference. This…
Articulated objects, as prevalent entities in human life, their 3D representations play crucial roles across various applications. However, achieving both high-fidelity textured surface reconstruction and dynamic generation for articulated…
Reconstructing objects from posed images is a crucial and complex task in computer graphics and computer vision. While NeRF-based neural reconstruction methods have exhibited impressive reconstruction ability, they tend to be…
3D Gaussian Splatting (3D-GS) has made a notable advancement in the field of neural rendering, 3D scene reconstruction, and novel view synthesis. Nevertheless, 3D-GS encounters the main challenge when it comes to accurately representing…
Open-set 3D segmentation represents a major point of interest for multiple downstream robotics and augmented/virtual reality applications. We present a decoupled 3D segmentation pipeline to ensure modularity and adaptability to novel 3D…
Localizing desired objects from remote sensing images is of great use in practical applications. Referring image segmentation, which aims at segmenting out the objects to which a given expression refers, has been extensively studied in…
The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and…
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…
3D Gaussian Splatting (3DGS) serves as a highly performant and efficient encoding of scene geometry, appearance, and semantics. Moreover, grounding language in 3D scenes has proven to be an effective strategy for 3D scene understanding.…
Humans naturally interact with their 3D surroundings using language, and modeling 3D language fields for scene understanding and interaction has gained growing interest. This paper introduces ChatSplat, a system that constructs a 3D…
Recent advances in leveraging large-scale Internet photo collections for 3D reconstruction have enabled immersive virtual exploration of landmarks and historic sites worldwide. However, little attention has been given to the immersive…
Gaussian Splatting has rapidly emerged as a transformative technique for real-time 3D scene representation, offering a highly efficient and expressive alternative to Neural Radiance Fields (NeRF). Its ability to render complex scenes with…
Humans live in a 3D world and commonly use natural language to interact with a 3D scene. Modeling a 3D language field to support open-ended language queries in 3D has gained increasing attention recently. This paper introduces LangSplat,…
Open-vocabulary panoptic reconstruction is a challenging task for simultaneous scene reconstruction and understanding. Recently, methods have been proposed for 3D scene understanding based on Gaussian splatting. However, these methods are…
Recent advancements in radiance fields have opened new avenues for creating high-quality 3D assets and scenes. Style transfer can enhance these 3D assets with diverse artistic styles, transforming creative expression. However, existing…
Recent advancements in camera-based occupancy prediction have focused on the simultaneous prediction of 3D semantics and scene flow, a task that presents significant challenges due to specific difficulties, e.g., occlusions and unbalanced…