WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images

2026-04-22

AI Summary

This work addresses the challenge of high-quality, real-time 3D reconstruction and appearance control from unconstrained images—where camera poses are unknown and lighting conditions vary significantly—by proposing a feed-forward 3D Gaussian Splatting model. The method jointly learns 3D Gaussians and image-conditioned appearance embeddings, enabling end-to-end sparse-view reconstruction and flexible appearance modulation without requiring known poses or consistent illumination. As the first approach to support end-to-end 3D Gaussian Splatting under pose-free, multi-illumination settings, it substantially outperforms existing pose-free 3DGS methods on real-world datasets, achieving reconstruction in under one second while enabling diverse appearance editing capabilities.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality, real-time rendering; however, it typically requires iterative optimization and multi-view images captured under consistent lighting with known camera parameters. WildSplatter is trained on unconstrained photo collections and jointly learns 3D Gaussians and appearance embeddings conditioned on input images. This design enables flexible modulation of Gaussian colors to represent significant variations in lighting and appearance. Our method reconstructs 3D Gaussians from sparse input views in under one second, while also enabling appearance control under diverse lighting conditions. Experimental results demonstrate that our approach outperforms existing pose-free 3DGS methods on challenging real-world datasets with varying illumination.

Problem

• 3D Gaussian Splatting
• unconstrained images
• appearance control
• unknown camera parameters
• varying lighting conditions

Innovation

• Feed-forward 3D Gaussian Splatting
• Appearance Control
• Unconstrained Images
• Pose-free Reconstruction
• Lighting Variation