WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Xuweiyi, Zhou, Wentao, Cheng, Zezhou
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909991658586112
author Chen, Xuweiyi
Zhou, Wentao
Cheng, Zezhou
author_facet Chen, Xuweiyi
Zhou, Wentao
Cheng, Zezhou
contents We present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments where both the camera and objects move. Dynamic content breaks the multi-view consistency that static NVS models rely on, leading to ghosting, hallucinated geometry, and unstable pose estimation. WildRayZer addresses this by performing an analysis-by-synthesis test: a camera-only static renderer explains rigid structure, and its residuals reveal transient regions. From these residuals, we construct pseudo motion masks, distill a motion estimator, and use it to mask input tokens and gate loss gradients so supervision focuses on cross-view background completion. To enable large-scale training and evaluation, we curate Dynamic RealEstate10K (D-RE10K), a real-world dataset of 15K casually captured dynamic sequences, and D-RE10K-iPhone, a paired transient and clean benchmark for sparse-view transient-aware NVS. Experiments show that WildRayZer consistently outperforms optimization-based and feed-forward baselines in both transient-region removal and full-frame NVS quality with a single feed-forward pass.
format Preprint
id arxiv_https___arxiv_org_abs_2601_10716
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments
Chen, Xuweiyi
Zhou, Wentao
Cheng, Zezhou
Computer Vision and Pattern Recognition
We present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments where both the camera and objects move. Dynamic content breaks the multi-view consistency that static NVS models rely on, leading to ghosting, hallucinated geometry, and unstable pose estimation. WildRayZer addresses this by performing an analysis-by-synthesis test: a camera-only static renderer explains rigid structure, and its residuals reveal transient regions. From these residuals, we construct pseudo motion masks, distill a motion estimator, and use it to mask input tokens and gate loss gradients so supervision focuses on cross-view background completion. To enable large-scale training and evaluation, we curate Dynamic RealEstate10K (D-RE10K), a real-world dataset of 15K casually captured dynamic sequences, and D-RE10K-iPhone, a paired transient and clean benchmark for sparse-view transient-aware NVS. Experiments show that WildRayZer consistently outperforms optimization-based and feed-forward baselines in both transient-region removal and full-frame NVS quality with a single feed-forward pass.
title WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.10716