paper-with-me

Papers

Geometric 4D Stitching for Grounded 4D Generation

2026-05-11 · Sunwoo Park, Taesung Kwon, Jong Chul Ye arxiv

Recent 4D generation methods complete scene-level missing information using generative models and reconstruct the scene into radiance-based representations. However, these pipelines often present geometric inconsistencies in the generated content, and the radiance-based reconstruction requires expensive optimization. Furthermore, radiance-based representations often absorb these geometric inconsistencies into their view-dependent nature, failing to enforce the grounded geometric consistency. To address these issues, we propose Geometric 4D Stitching, an efficient framework that explicitly identifies missing geometric regions and complements them with geometrically grounded 4D stitches. As a result, our method constructs 4D scene representations in under 10 minutes on a single NVIDIA RTX 5090 GPU per one-step scene expansion, while improving geometric consistency. Moreover, we demonstrate that our explicit 4D stitching supports interative expansion of 4D mesh as well as 4D scene editing.

📄 PDF Abstract BibTeX arXiv:2605.09984

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Geometric Structure Preserving Warp for Natural Image Stitching

2022-01-01 · CVPR 2022 1 · Peng Du, Jifeng Ning, Jiguang Cui, Shaoli Huang 외

Preserving geometric structures in the scene plays a vital role in image stitching. However, most of the existing methods ignore the large-scale layouts reflected by straight lines or curves, decreasing overall stitc…

Edge DetectionImage Stitching

PIS3R: Very Large Parallax Image Stitching via Deep 3D Reconstruction

2025-08-06 · Muhua Zhu, Xinhao Jin, Chengbo Wang, Yongcong Zhang 외 arxiv

Image stitching aim to align two images taken from different viewpoints into one seamless, wider image. However, when the 3D scene contains depth variations and the camera baseline is significant, noticeable parallax occ…

3D ReconstructionImage Stitching

UniStitch: Unifying Semantic and Geometric Features for Image Stitching

2026-03-11 · Yuan Mei, Lang Nie, Kang Liao, Yunqiu Xu 외 arxiv

Traditional image stitching methods estimate warps from hand-crafted geometric features, whereas recent learning-based solutions leverage semantic features from neural networks instead. These two lines of research have l…

Image Stitching

Generalized Content-Preserving Warps for Image Stitching

2018-09-18 · Kai Chen, Jingmin Tu, Jian Yao

Local misalignment caused by global homography is a common issue in image stitching task. Content-Preserving Warping (CPW) is a typical method to deal with this issue, in which geometric and photometric constraints are i…

Image Stitching

Multiple Combined Constraints for Image Stitching

2018-09-18 · Kai Chen, Jingmin Tu, Binbin Xiang, Li Li 외

Several approaches to image stitching use different constraints to estimate the motion model between image pairs. These constraints can be roughly divided into two categories: geometric constraints and photometric constr…

Image Stitching