This repository is a curated list of research papers, datasets, and applications focused on feed-forward 3D scene modeling. It serves as a comprehensive resource for researchers and practitioners in computer vision and graphics, aiming to accelerate advancements in creating and understanding 3D environments from 2D inputs.

How It Works

The list organizes numerous research directions, including advanced encoding architectures, cross-view fusion techniques, integration with visual foundation models, geometry-aware improvements, and pose-free reconstruction methods. It highlights a shift towards efficient, feed-forward models that can generate 3D representations rapidly, often leveraging techniques like Gaussian Splatting and large reconstruction models (LRMs).

Quick Start & Requirements

This repository is a curated list of research papers and code repositories, not a single installable project. Therefore, there are no direct installation or quick-start instructions for the list itself. Users are directed to individual project links for setup and requirements.

Highlighted Details

• Covers a wide spectrum of research directions, from fundamental geometry-aware improvements to advanced applications in autonomous driving and robotics.
• Features a significant focus on recent advancements in Gaussian Splatting and Large Reconstruction Models (LRMs) for efficient 3D generation.
• Includes a comprehensive taxonomy of datasets and benchmarks relevant to 3D scene modeling.

Maintenance & Community

No specific information regarding maintenance, contributors, or community channels (like Discord or Slack) is provided in the README.

Licensing & Compatibility

The README does not specify a license for the curated list itself. Users should refer to the licenses of individual projects linked within the list.

Limitations & Caveats

As a curated list, this repository does not have inherent limitations in terms of functionality or performance. However, the adoption and applicability of the listed research depend entirely on the individual projects' maturity, requirements (e.g., hardware, specific datasets), and licensing.