CORTEXA
← Browse
arxivcs.CV2026-07-06

WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images

Xiyu Zhang, Jingyu Zhuang, Hongjia Zhai, Zizheng Yan, Jinwei Chen, Guofeng Zhang, Qingnan Fan

While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce WildSplat, the first feedforward 3D Gaussian Splatting framework capable of appearance-conditioned novel-view synthesis for unposed in-the-wild images. To handle inconsistent photometric conditions, we propose a dual-branch architecture that explicitly decouples geometry from appearance. The geometry branch extracts an appearance-invariant 3D structure and jointly predicts camera poses. To govern the rendering appearance, the appearance branch injects target appearance cues into the content features via a globally pre-modulated cross-attention mechanism. To further prevent feature entanglement, we introduce a joint multi-reference training strategy that stabilizes the training process. Extensive experiments show that WildSplat surpasses existing optimization-based and feedforward methods, achieving state-of-the-art performance in in-the-wild novel view synthesis and appearance editing from sparse inputs in a single forward pass.

View free PDFSource page

Related papers

arxivcs.CV2026-07-31

OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting

Zhisheng Han, Shiyao Wu, Jiayan Qiu, Yakun Ju, Lu Liu, Le Zhang, et al.

Single-image 3D hand avatar reconstruction is fundamentally ill-posed and particularly challenging due to limited visual evidence under severe self-occlusion and the complex pose-dependent deformation of highly articulated hands. Existing methods predominantly rely on implicit Ne…

View free PDFSource page
arxivcs.CV2026-07-22

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

Cho In, Jeonghwan Cho, Mijin Yoo, Gim Hee Lee, Seon Joo Kim

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 allocation is largely lost in existing feed-forward 3DGS metho…

View free PDFSource page
arxivcs.CV2026-07-31

FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement

Takashi Otonari, Toshihiko Yamasaki

4D Gaussian Splatting (4DGS) can render dynamic scenes photorealistically. However, with limited viewpoint coverage, some spatiotemporal regions remain sparsely observed, leading to artifacts, particularly in scenes with large motion. Existing approaches leveraging generative mod…

View free PDFSource page
arxivcs.CV2026-07-22

Look Before You Edit: Attention-Guided Camera Placement and Multi-View Alignment for 3D Gaussian Splatting Editing

Jaeyeon Park, Taeho Kang, Youngki Lee

Text-driven 3D scene editing with 3D Gaussian Splatting (3DGS) typically applies a 2D diffusion editor to views rendered from fixed training cameras, limiting both the spatial coverage of edits and the user's freedom to target specific objects in complex scenes. We present LB-Edi…

View free PDFSource page
arxivcs.CV2026-07-23

GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis

Jiahao He, Yihua Shao, Zhengkai Zhao, Pan Gao, Fei Ma, Jingcai Guo, et al.

Dynamic scene reconstruction with 3D Gaussian Splatting requires a balance between fine-grained motion modeling, structural stability, and compact representation. Existing per-primitive methods provide flexible local deformation but often suffer from redundant primitive growth, w…

View free PDFSource page