# FurnSet: Exploiting Repeats for 3D Scene Reconstruction Source: [FurnSet: Exploiting Repeats for 3D Scene Reconstruction]() Collection index: [llms.txt]() Data updated: 2026-04-24T05:00:04.605Z Authors: Paul Dobre, Xin Wang, Hongzhou Yang Published: 2026-04-22T01:27:13.000Z ## Abstract Single-view 3D scene reconstruction involves inferring both object geometry and spatial layout. Existing methods typically reconstruct objects independently or rely on implicit scene context, failing to exploit the repeated instances commonly present in realworld scenes. We propose FurnSet, a framework that explicitly identifies and leverages repeated object instances to improve reconstruction. Our method introduces per-object CLS tokens and a set-aware self-attention mechanism that groups identical instances and aggregates complementary observations across them, enabling joint reconstruction. We further combine scene-level and object-level conditioning to guide object reconstruction, followed by layout optimization using object point clouds with 3D and 2D projection losses for scene alignment. Experiments on 3D-Future and 3D-Front demonstrate improved scene reconstruction quality, highlighting the effectiveness of exploiting repetition for robust 3D scene reconstruction. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [3D Scene Reconstruction on 3D-Future & 3D-Front](): 3D Scene Reconstruction; 3D-Future & 3D-Front; CD-S: 0.0451. - [3D Scene Reconstruction on 3D-Future & 3D-Front Repeated Instances](): 3D Scene Reconstruction; 3D-Future & 3D-Front Repeated Instances; CD-O: 0.0281. ## Original sources and implementation [Original paper]() [PDF]()