Related papers: Position: 3D Gaussian Splatting Watermarking Shoul…
Engineering a top-notch deep learning model is an expensive procedure that involves collecting data, hiring human resources with expertise in machine learning, and providing high computational resources. For that reason, deep learning…
3D Gaussian Splatting (3DGS) has become increasingly popular in 3D scene reconstruction for its high visual accuracy. However, uncertainty estimation of 3DGS scenes remains underexplored and is crucial to downstream tasks such as asset…
Dynamic scene reconstruction has garnered significant attention in recent years due to its capabilities in high-quality and real-time rendering. Among various methodologies, constructing a 4D spatial-temporal representation, such as 4D-GS,…
The advent of 3D Gaussian Splatting (3DGS) has recently brought about a revolution in the field of neural rendering, facilitating high-quality renderings at real-time speed. However, 3DGS heavily depends on the initialized point cloud…
Artificial Intelligence Generated Content (AIGC), particularly video generation with diffusion models, has been advanced rapidly. Invisible watermarking is a key technology for protecting AI-generated videos and tracing harmful content, and…
Abstract representations of 3D scenes play a crucial role in computer vision, enabling a wide range of applications such as mapping, localization, surface reconstruction, and even advanced tasks like SLAM and rendering. Among these…
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…
Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations…
3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling scenes affected by transient…
Open-vocabulary 3D scene understanding is crucial for robotics applications, such as natural language-driven manipulation, human-robot interaction, and autonomous navigation. Existing methods for querying 3D Gaussian Splatting often…
Novel view synthesis has seen significant advancements with 3D Gaussian Splatting (3DGS), enabling real-time photorealistic rendering. However, the inherent fuzziness of Gaussian Splatting presents challenges for 3D scene understanding,…
Recent advances in 3D Gaussian Splatting (3DGS) have focused on accelerating optimization while preserving reconstruction quality. However, many proposed methods entangle implementation-level improvements with fundamental algorithmic…
3D intelligence leverages rich 3D features and stands as a promising frontier in AI, with 3D rendering fundamental to many downstream applications. 3D Gaussian Splatting (3DGS), an emerging high-quality 3D rendering method, requires…
3D Gaussian Splatting (3DGS) under raindrop conditions suffers from severe occlusions and optical distortions caused by raindrop contamination on the camera lens, substantially degrading reconstruction quality. Existing benchmarks typically…
While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributions introduces visual artifacts that hinder accurate spatial data exploration.…
Recently, 3D Gaussian Splatting has emerged as a promising approach for modeling 3D scenes using mixtures of Gaussians. The predominant optimization method for these models relies on backpropagating gradients through a differentiable…
Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real-time novel-view synthesis with high visual quality and fast training times.…
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).…
3D Gaussian Splatting (3DGS) achieves high-fidelity rendering with fast real-time performance, but existing methods rely on offline training after full Structure-from-Motion (SfM) processing. In contrast, this work introduces Gaussian…
Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a…