notesum.ai
Published at December 4MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
cs.CV
Released Date: December 4, 2024
Authors: Zehuan Huang1, Yuan-Chen Guo2, Xingqiao An3, Yunhan Yang4, Yangguang Li2, Zi-Xin Zou2, Ding Liang2, Xihui Liu4, Yan-Pei Cao2, Lu Sheng1
Aff.: 1Beihang University; 2VAST; 3Tsinghua University; 4The University of Hong Kong
![[Uncaptioned image]](https://arxiv.org/html/2412.03558v1/x1.png)
| Method | 3D-Front | BlendSwap | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| CD-S | F-Score-S | CD-O | F-Score-O | IoU-B | CD-S | F-Score-S | CD-O | F-Score-O | IoU-B | Runtime | |
| PanoRecon [7] | 0.150 | 40.65 | 0.211 | 35.05 | 0.240 | 0.427 | 19.11 | 0.713 | 13.06 | 0.119 | 32s |
| Total3D [45] | 0.270 | 32.90 | 0.179 | 36.38 | 0.238 | 0.258 | 37.93 | 0.168 | 38.14 | 0.328 | 39s |
| InstPIFu [35] | 0.138 | 39.99 | 0.165 | 38.11 | 0.299 | 0.129 | 50.28 | 0.167 | 38.42 | 0.340 | 32s |
| SSR [4] | 0.140 | 39.76 | 0.170 | 37.79 | 0.311 | 0.132 | 48.72 | 0.173 | 38.11 | 0.336 | 32s |
| DiffCAD [17] | 0.117 | 43.58 | 0.190 | 37.45 | 0.392 | 0.110 | 52.83 | 0.169 | 38.98 | 0.457 | 64s |
| Gen3DSR [11] | 0.123 | 40.07 | 0.157 | 38.11 | 0.363 | 0.107 | 60.17 | 0.148 | 40.76 | 0.449 | 9min |
| REPARO [20] | 0.129 | 41.68 | 0.160 | 40.85 | 0.339 | 0.115 | 62.39 | 0.151 | 42.84 | 0.410 | 4min |
| Ours | 0.080 | 50.19 | 0.103 | 53.58 | 0.518 | 0.077 | 78.21 | 0.090 | 62.94 | 0.663 | 40s |