SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.00144 · 2024

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
sailor-z/se-gs canonical 4 of 9
FunctionStatusWhere it lives
read_cameras_text Ran sailor-z/se-gs/utils/colmap_read_model.py
pointer only (licence: NONE) · get_code("8a38e306ff4c5b42")
read_next_bytes Ran sailor-z/se-gs/utils/colmap_read_model.py
pointer only (licence: NONE) · get_code("56858e04e6fdb2ff")
visualize_cmap Ran sailor-z/se-gs/spiral.py
pointer only (licence: NONE) · get_code("46959ddc3b4a8888")
weighted_percentile Ran sailor-z/se-gs/spiral.py
pointer only (licence: NONE) · get_code("9a7dd063ea98b616")
custom_sort Not yet run sailor-z/se-gs/metrics_dtu.py
pointer only (licence: NOASSERTION) · get_code("f8a568a9009f4ade")
get_cam_dis Not yet run sailor-z/se-gs/train_mvimgnet.py
pointer only (licence: NOASSERTION) · get_code("25e8eb8ff1dffb08")
readImages Not yet run sailor-z/se-gs/metrics.py
pointer only (licence: NONE) · get_code("2a05973a17f517e6")
readImages Not yet run sailor-z/se-gs/metrics_dtu.py
pointer only (licence: NOASSERTION) · get_code("f0a7e7830ac7d9d7")
read_cameras_binary Not yet run sailor-z/se-gs/utils/colmap_read_model.py
pointer only (licence: NONE) · get_code("3d7e294ff8567d46")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in novel view synthesis (NVS). However, 3DGS tends to overfit when trained with sparse views, limiting its generalization to novel viewpoints. In this paper, we address this overfitting issue by introducing Self-Ensembling Gaussian Splatting (SE-GS). We achieve self-ensembling by incorporating an uncertainty-aware perturbation strategy during training. A $\mathbfΔ$-model and a $\mathbfΣ$-model are jointly trained on the available images. The $\mathbfΔ$-model is dynamically perturbed based on rendering uncertainty across training steps, generating diverse perturbed models with negligible computational overhead. Discrepancies between the $\mathbfΣ$-model and these perturbed models are minimized throughout training, forming a robust ensemble of 3DGS models. This ensemble, represented by the $\mathbfΣ$-model, is then used to generate novel-view images during inference. Experimental results on the LLFF, Mip-NeRF360, DTU, and MVImgNet datasets demonstrate that our approach enhances NVS quality under few-shot training conditions, outperforming existing state-of-the-art methods. The code is released at: https://sailor-z.github.io/projects/SEGS.html.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2411.00144")
get_code_for_paper("2411.00144")
have("2411.00144")

Connect an agent — have() is free.