跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20433 · v2

ReScene: Incremental Scene Chronology from Sparse Revisits

首次提交 2026-11-16 10:52
版本更新 2026-11-17 16:23
雷达观测 2026-11-18 19:42
arXiv ↗PDF ↗

摘要

Scene chronology aims to reconstruct a scene across visits separated by hours or days, during which objects may change in position, presence or shape. Such reconstruction must retain every earlier state, yet each revisit often provides only a few images. Storing a complete model for each visit duplicates the unchanged scene, whereas updating a single shared model alters earlier states. We present ReScene, which stores each visit as an immutable compact update, so that any earlier visit can be recovered exactly by applying the stored updates in order, without retaining past images. To localise each update, ReScene attributes the disagreement between the preceding reconstruction and the new images to individual Gaussians through their compositing weights. This attribution guides the suppression of outdated Gaussians and the refinement of persistent ones, while newly visible surfaces are initialised from learned multi-view depth. We also introduce Multi-State, a benchmark of non-rigid deformation and partial material removal, including synthetic scenes with ground-truth geometry. ReScene achieves quality higher than sequential 3DGS checkpointing with 2.5--4.8×\times less uncompressed history storage. At comparable PSNR, it also reduces foreground depth error by 3.2×\times relative to sequential ChronoGS, showing that accurate rendering does not necessarily imply accurate geometry. Code and benchmark are available at https://waychin-weiqin.github.io/ReScene/.

作者备注:22 pages

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

仅对比实际观测的元数据,不代表 PDF 正文或实验变化。版本可能不连续;带删除线为移除,下划线为新增。

这两个版本的已观测标题、作者、分类、摘要和备注没有变化。正文是否变化请核对原文。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-17 16:23 · 最新观测版本

ReScene: Incremental Scene Chronology from Sparse Revisits

Scene chronology aims to reconstruct a scene across visits separated by hours or days, during which objects may change in position, presence or shape. Such reconstruction must retain every earlier state, yet each revisit often provides only a few images. Storing a complete model for each visit duplicates the unchanged scene, whereas updating a single shared model alters earlier states. We present ReScene, which stores each visit as an immutable compact update, so that any earlier visit can be recovered exactly by applying the stored updates in order, without retaining past images. To localise each update, ReScene attributes the disagreement between the preceding reconstruction and the new images to individual Gaussians through their compositing weights. This attribution guides the suppression of outdated Gaussians and the refinement of persistent ones, while newly visible surfaces are initialised from learned multi-view depth. We also introduce Multi-State, a benchmark of non-rigid deformation and partial material removal, including synthetic scenes with ground-truth geometry. ReScene achieves quality higher than sequential 3DGS checkpointing with 2.5--4.8×\times less uncompressed history storage. At comparable PSNR, it also reduces foreground depth error by 3.2×\times relative to sequential ChronoGS, showing that accurate rendering does not necessarily imply accurate geometry. Code and benchmark are available at https://waychin-weiqin.github.io/ReScene/.

查看此版本解读 →查看此版本原文 ↗
v1 · 2026-11-16 10:52

ReScene: Incremental Scene Chronology from Sparse Revisits

Scene chronology aims to reconstruct a scene across visits separated by hours or days, during which objects may change in position, presence or shape. Such reconstruction must retain every earlier state, yet each revisit often provides only a few images. Storing a complete model for each visit duplicates the unchanged scene, whereas updating a single shared model alters earlier states. We present ReScene, which stores each visit as an immutable compact update, so that any earlier visit can be recovered exactly by applying the stored updates in order, without retaining past images. To localise each update, ReScene attributes the disagreement between the preceding reconstruction and the new images to individual Gaussians through their compositing weights. This attribution guides the suppression of outdated Gaussians and the refinement of persistent ones, while newly visible surfaces are initialised from learned multi-view depth. We also introduce Multi-State, a benchmark of non-rigid deformation and partial material removal, including synthetic scenes with ground-truth geometry. ReScene achieves quality higher than sequential 3DGS checkpointing with 2.5--4.8×\times less uncompressed history storage. At comparable PSNR, it also reduces foreground depth error by 3.2×\times relative to sequential ChronoGS, showing that accurate rendering does not necessarily imply accurate geometry. Code and benchmark are available at https://waychin-weiqin.github.io/ReScene/.

查看此版本解读 →查看此版本原文 ↗