paper-with-me

홈 › Papers

TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction

2026-02-28 · Yihui Li, Chengxin Lv, Zichen Tang, Hongyu Yang, Di Huang arxiv

We present TokenSplat, a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation from unposed multi-view images. At its core, TokenSplat introduces a Token-aligned Gaussian Prediction module that aligns semantically corresponding information across views directly in the feature space. Guided by coarse token positions and fusion confidence, it aggregates multi-scale contextual features to enable long-range cross-view reasoning and reduce redundancy from overlapping Gaussians. To further enhance pose robustness and disentangle viewpoint cues from scene semantics, TokenSplat employs learnable camera tokens and an Asymmetric Dual-Flow Decoder (ADF-Decoder) that enforces directionally constrained communication between camera and image tokens. This maintains clean factorization within a feed-forward architecture, enabling coherent reconstruction and stable pose estimation without iterative refinement. Extensive experiments demonstrate that TokenSplat achieves higher reconstruction fidelity and novel-view synthesis quality in pose-free settings, and significantly improves pose estimation accuracy compared to prior pose-free methods. Project page: https://kidleyh.github.io/tokensplat/.

📄 PDF Abstract BibTeX arXiv:2603.00697

Code (0)

등록된 구현이 없습니다.

Tasks

Camera Pose Estimation

Similar Papers 제목 키워드 기반

ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion

2026-07-22 · Cho In, Jeonghwan Cho, Mijin Yoo, Gim Hee Lee 외 hf

3D Gaussian Splatting (3DGS) achieves high-quality novel-view synthesis by optimizing freely placed primitives in 3D and adaptively densifying them in under-reconstructed regions. However, this scene-adaptive capacity al…

ZipSplat: Fewer Gaussians, Better Splats

2026-06-03 · Alexander Veicht, Sunghwan Hong, Dániel Baráth, Marc Pollefeys arxiv

Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel, tying the representation budget to came…

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

2026-03-26 · Yixing Lao, Xuyang Bai, Xiaoyang Wu, Nuoyuan Yan 외 arxiv

Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-res…

Novel View Synthesis

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

2025-09-23 · Weijie Wang, Yeqing Chen, Zeyu Zhang, Hengyu Liu 외 arxiv

Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pix…

Novel View Synthesis

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

2026-04-16 · Roni Itkin, Noam Issachar, Yehonatan Keypur, Xingyu Chen 외 arxiv

The efficient spatial allocation of primitives serves as the foundation of 3D Gaussian Splatting, as it directly dictates the synergy between representation compactness, reconstruction speed, and rendering fidelity. Prev…