← Back to all news
arXiv Computer Vision By Muhua Zhu, Xinhao Jin, Chengbo Wang, Yongcong Zhang, Yifei Xue, Tie Ji, Yizhen Lao

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

Read the original on arXiv Computer Vision →

PIS3R is an image stitching method designed to handle very large parallax by leveraging deep 3D reconstruction. It uses a visual geometry grounded transformer to estimate camera parameters and reconstruct a dense 3D point cloud from two input images, then reprojects this cloud onto a reference view to create an initial stitched image. A point-conditioned image diffusion module refines the result, reducing artifacts such as holes or noise.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 23

Squaring-the-Sphere: Distortion-Free and Seamless Panorama Generation via CubeAtlas

Squaring-the-Sphere introduces CubeAtlas, a new panoramic representation that unifies all cubemap faces into a single canvas, preserving perspective geometry while enabling seamless panorama assembly. The framework leverages a pretrained diffusion transformer with a layout‑aware sparse attention mask to reduce irrelevant token interactions, achieving higher quality than equirectangular projection with lower computational cost. Additionally, a training‑free super‑resolution and fusion scheme enhances fine details before converting to a final ERP panorama, resulting in improved geometric fidelity, cross‑view consistency, and high‑resolution visual quality across benchmarks.

By Xuhui Zuo, Chenjie Cao, Tengfei Wang, Junta Wu, Yisu Zhang, Chunchao Guo
llmsdiffusionbenchmarks
More like this →
arXiv Computer Vision
Oct 26

CompMVR: Compression-Aware Multi-View Restoration Using Diffusion Models for Geometrically Consistent 3D Reconstruction

arXiv:2610.32800v1 Announce Type: new Abstract: Real-world 3D reconstruction pipelines often rely on multi-view images degraded by lossy compression. While compression artifacts have been extensively...

By Dong-hwi Kim, Chaewon Moon, Hojun Song, Dongbeom Kim, Junyeong Jang, Aro Kim, Gahyeon Kim, Heejung Choi, Jehee Kim, Gianella Cravioto, Sohyun Lee, Gyeongjin Choi, EunHye Jeong, Soo Ye Kim, Jaehyup Lee, Sang-hyo Park
diffusioncomputer-vision
More like this →
arXiv Computer Vision
Oct 5

T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images

T3lescope is a generative surface reconstruction method that produces high‑fidelity 3D meshes from posed multi‑view images without per‑scene optimization. It uses a single fixed‑resolution generator in a coarse‑to‑fine cascade, where each level refines geometry within progressively finer spatial cells. Trained on cells at multiple scales, the model shares weights across all levels, allowing it to adapt the number of levels, cell scales, and locations at inference time and achieve consistent geometry across indoor, outdoor, and city‑scale scenes.

By Atsuhiro Noguchi, Tianhan Xu, Yiming Liang, Yuta Kikuchi, Masahiro Ishiyama, Shintaro Takagi, Hitoshi Murai, Eiichi Matsumoto
More like this →