Papers › HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features
HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features
Cheng Sun, Min Sun, Hwann-Tzong Chen
We present HoHoNet, a versatile and efficient framework for holistic understanding of an indoor 360-degree panorama using a Latent Horizontal Feature (LHFeat). The compact LHFeat flattens the features along the vertical direction and has shown success in modeling per-column modality for room layout reconstruction. HoHoNet advances in two important aspects. First, the deep architecture is redesigned to run faster with improved accuracy. Second, we propose a novel horizon-to-dense module, which relaxes the per-column output shape constraint, allowing per-pixel dense prediction from LHFeat. HoHoNet is fast: It runs at 52 FPS and 110 FPS with ResNet-50 and ResNet-34 backbones respectively, for modeling dense modalities from a high-resolution 512 ×1024 panorama. HoHoNet is also accurate. On the tasks of layout estimation and semantic segmentation, HoHoNet achieves results on par with current state-of-the-art. On dense depth estimation, HoHoNet outperforms all the prior arts by a large margin.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Room Layouts From A Single RGB Panorama | Stanford2D3D Panoramic | HoHoNet (ResNet-101) | 3DIoU | 79.88 | #6 of 9 | Archive leaderboard | report |
| Depth Estimation | Stanford2D3D Panoramic | HoHoNet (ResNet-101) | RMSE | 0.3834 | #14 of 18 | Archive leaderboard | report |
| Depth Estimation | Stanford2D3D Panoramic | HoHoNet (ResNet-101) | absolute relative error | 0.1014 | #14 of 18 | Archive leaderboard | report |
| Semantic Segmentation | Stanford2D3D Panoramic | HoHoNet (ResNet-101) | mAcc | 65.0 | #13 of 25 | Archive leaderboard | report |
| Semantic Segmentation | Stanford2D3D Panoramic | HoHoNet (ResNet-101) | mIoU | 52.0% | #13 of 25 | Archive leaderboard | report |
| Semantic Segmentation | Stanford2D3D Panoramic - RGBD | HoHoNet (ResNet-101) | mAcc | 68.9 | #3 of 3 | Archive leaderboard | report |
| Semantic Segmentation | Stanford2D3D Panoramic - RGBD | HoHoNet (ResNet-101) | mIoU | 56.3 | #3 of 3 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections