← Back to all news
arXiv AI By Qizhou Huo, Xuan Sun, Yongfei Guo, Zhipeng Wang, Yuanhao Gong

LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views

Read the original on arXiv AI →

The paper introduces LVS, a framework that replaces repeated rendering of nearby views in interactive scene exploration with relative‑pose‑guided RGB‑D image reuse. It uses geometric warping based on depth and pose to transport source content, and a lightweight multiscale network to predict RGB residuals that correct artifacts and fill in missing appearance. Cached source features further reduce computation, yielding a 0.72 dB PSNR improvement over pure warping and low query latency on both captured and rendered scenes.

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 AI.

Related stories

arXiv Computer Vision
Sep 4

Stabilizing Camera-Controlled Novel View Synthesis at Inference Time

The paper introduces CamTrol++, a training‑free method that stabilizes camera‑controlled novel view synthesis from a single image by decomposing large camera motions into small autoregressive steps, thereby limiting per‑step distortion and error accumulation. It also incorporates geometry‑constrained spatial attention, low‑frequency appearance anchoring, and a registration‑free warping pipeline to further enhance stability. Experiments on RealEstate10K and MegaScene demonstrate improved temporal and geometric consistency, better downstream 3D reconstruction quality, and higher generation efficiency, even for long 56‑frame sequences and under depth corruption.

By Prajwal Singh, Arjun Badola, Seema Kumari, Hajime Nagahara, Shanmuganathan Raman
diffusion
More like this →
arXiv Computer Vision
Oct 9

LVSPM: Long Sequence View Synthesis and Pose Estimation Model

LVSPM is a generalizable model that jointly estimates camera poses and synthesizes novel views from uncalibrated image collections. It is trained only with RGB images and pose supervision, avoiding dense 3D ground truth, and uses test‑time training layers to scale to hundreds of input views. On datasets such as RealEstate10k, Co3Dv2, and DL3DV, LVSPM outperforms VGGT in pose estimation across 16–256 views and achieves state‑of‑the‑art pose‑free novel view synthesis quality, maintaining high performance even as scene scale increases.

By Xi Chen, Yachi Zhang, Linghao Chen, Minghua Liu, Hao Su, Zexiang Xu, Xiaoshuai Zhang
computer-visionbenchmarks
More like this →