AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

We introduce AnySplat, a feed-forward network for novel-view synthesis from uncalibrated image collections. In contrast to traditional neural-rendering pipelines that demand known camera poses and per-scene optimization, or recent feed-forward methods that buckle under the computational weight of dense views—our model predicts everything in one shot. A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance, and the corresponding camera intrinsics and extrinsics for each input image. This unified design scales effortlessly to casually captured, multi-view datasets without any pose annotations. In extensive zero-shot evaluations, AnySplat matches the quality of pose-aware baselines in both sparse- and dense-view scenarios while surpassing existing pose-free approaches. Moreover, it greatly reduces rendering latency compared to optimization-based neural fields, bringing real-time novel-view synthesis within reach for unconstrained capture settings. Project page: https://city-super.github.io/anysplat/.

Authors

Institutions

Publication Details

Journal
ACM Transactions on Graphics
Published
2025-12-01
DOI
https://doi.org/10.1145/3763326
Citations
2
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
article
Field-Weighted Citation Impact
2.55
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Dahua Lin, Jiangmiao Pang, Linning Xu, Mulin Yu et al.
2 citations
ACM Transactions on Graphics
Generative Adversarial Networks and Image Synthesis
2.55
article

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

Dahua Lin, Jiangmiao Pang, Linning Xu, Mulin Yu, Feng Zhao, Tao Lu, Bo Dai, Yichen Jin, Kerui Ren, Yucheng Mao, Lihan Jiang, Xudong Xu
article en
2 citations

Abstract

We introduce AnySplat, a feed-forward network for novel-view synthesis from uncalibrated image collections. In contrast to traditional neural-rendering pipelines that demand known camera poses and per-scene optimization, or recent feed-forward methods that buckle under the computational weight of dense views—our model predicts everything in one shot. A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance, and the corresponding camera intrinsics and extrinsics for each input image. This unified design scales effortlessly to casually captured, multi-view datasets without any pose annotations. In extensive zero-shot evaluations, AnySplat matches the quality of pose-aware baselines in both sparse- and dense-view scenarios while surpassing existing pose-free approaches. Moreover, it greatly reduces rendering latency compared to optimization-based neural fields, bringing real-time novel-view synthesis within reach for unconstrained capture settings. Project page: https://city-super.github.io/anysplat/.

ACM Transactions on GraphicsVol. 44(6)
University of Science and Technology of China (CN), Chinese University of Hong Kong (HK), Shanghai Jiao Tong University (CN), Brown University (US), Beijing Academy of Artificial Intelligence (CN), Artificial Intelligence in Medicine (Canada) (CA), Shanghai Artificial Intelligence Laboratory (CN), University of Hong Kong (HK)
Openalex Percentile: Top 8%
Generative Adversarial Networks and Image Synthesis
2.55
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.