Abstract
Pose-free feed-forward 3D Gaussian Splatting (3DGS) has demonstrated remarkable potential for generalized novel view synthesis. However, existing methods typically predict Gaussian appearance attributes represented by spherical harmonics (SH) in the same manner, overlooking the fundamental distinction between view-independent and view-dependent appearance, which results in suboptimal rendering quality. In this paper, we present AESplat, a novel and general framework for pose-free feed-forward 3DGS that introduces an effective decoupled appearance modeling strategy based on an analysis of SH, enabling higher-quality rendering. Specifically, AESplat directly derives the zeroth-order SH coefficient, which represents the base view-independent appearance component, from the input images without training. The higher-order SH coefficients are subsequently predicted by a shallow multilayer perceptron equipped with two efficient 3D-aware inductive biases to model view-dependent appearance variations. Extensive experiments across multiple datasets demonstrate that our method significantly outperforms state-of-the-art approaches, achieving a $0.8$ dB improvement in PSNR over the pose-free method NAS3R and a $1.1$ dB improvement over the pose-required method DepthSplat on the RealEstate10K dataset. Project page: https://aesplat.github.io/.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ren, S., Liu, Z., Fang, Y., & Chen, H. (2026). AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling. https://omanscience.com/en/articles/aesplat-advancing-pose-free-feed-forward-3d-gaussian-splatting-via-decoupled-appearance-modeling
MLA 9
Ren, Shiwei, et al. "AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling." https://omanscience.com/en/articles/aesplat-advancing-pose-free-feed-forward-3d-gaussian-splatting-via-decoupled-appearance-modeling.
Chicago (author–date)
Ren, Shiwei, Zhiang Liu, Yongchun Fang, and Hongwei Chen. 2026. "AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling." https://omanscience.com/en/articles/aesplat-advancing-pose-free-feed-forward-3d-gaussian-splatting-via-decoupled-appearance-modeling.
Harvard
Ren, S., Liu, Z., Fang, Y. and Chen, H. (2026) 'AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling', Available at: https://omanscience.com/en/articles/aesplat-advancing-pose-free-feed-forward-3d-gaussian-splatting-via-decoupled-appearance-modeling.
Vancouver
Ren S, Liu Z, Fang Y, Chen H. AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling. https://omanscience.com/en/articles/aesplat-advancing-pose-free-feed-forward-3d-gaussian-splatting-via-decoupled-appearance-modeling
IEEE
S. Ren, Z. Liu, Y. Fang, and H. Chen, "AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling," https://omanscience.com/en/articles/aesplat-advancing-pose-free-feed-forward-3d-gaussian-splatting-via-decoupled-appearance-modeling.