Research map / 3D vision / Depth and stereo
RigNet: Repetitive Image Guided Network for Depth Completion
Zhiqiang Yan, Kun Wang, Xiang Li, Zhenyu Zhang, Jun Li, Jian Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| deepen single image-guidance backbone from ResNet-18 to 26/34/50 (ablation) | GuideNet-style baseline · KITTI validation | RMSE (mm): 779 -> 777 | No clear effect |
| replace ResNet-10 with ResNet-18 backbone (ablation) | image guidance branch · KITTI validation | RMSE (mm): 822 -> 779 | Improved |
| stack hourglass units in tandem (18-2/18-3/18-4) (ablation) | image guidance branch · KITTI validation | RMSE (mm): 779 -> 816 | Hurt |
| use deeper tandem hourglass units (Deeper-More) (ablation) | image guidance branch · KITTI validation | RMSE (mm): 779 -> 807 | Hurt |
| add parallel repetitive hourglass network (RHN 18-3) (ablation) | baseline ResNet-18 · KITTI validation | RMSE (mm): 779 -> 769 | Improved |
| replace raw guided convolution G1 with efficient guidance EG1 (ablation) | RigNet · KITTI validation | GPU memory (GB): +1.35 -> -10.60 | Improved |
| repeat efficient guidance twice (EG1,2) (ablation) | RigNet · KITTI validation | RMSE (mm): 768.6 -> 762.3 | Improved |
| repeat efficient guidance three times (EG1,2,3) (ablation) | RigNet · KITTI validation | RMSE (mm): 768.6 -> 757.4 | Improved |
| add fusion of repeated outputs by addition (ablation) | RigNet (d) · KITTI validation | RMSE (mm): 757.4 -> 755.8 | Improved |
| add adaptive fusion instead of addition or concatenation (ablation) | RigNet (d) · KITTI validation | RMSE (mm): 757.4 -> 752.1 | Improved |
| use efficient guidance instead of common dynamic convolution | guidance module · GPU memory in one fusion stage | memory (GB): 42.75 -> 0.037 | Improved |
Later papers that compared with this method
11 later accepted papers report RigNet as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.
- PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning (CVPR 2026 · better on 4 of 4 shared results)
- Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models (ICLR 2026 · better on 3 of 3 shared results)
- Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters (CVPR 2025 · better on 6 of 6 shared results)
- MagicArticulate: Make Your 3D Models Articulation-Ready (CVPR 2025 · better on 5 of 5 shared results)
- RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion (IJCV 2025 · better on 5 of 5 shared results)
- DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters (CVPR 2025 · better on 3 of 3 shared results)
- ARMO: Autoregressive Rigging for Multi-Category Objects (ICCV 2025 · better on 3 of 3 shared results)
- HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset (CVPR 2025 · better on 1 of 1 shared result)
3 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FCFRNet — FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion (AAAI 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion (IJCV 2025 · similarity 0.97)
- CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion (AAAI 2020 · similarity 0.90)
- GuideFormer: Transformers for Image Guided Depth Completion (CVPR 2022 · similarity 0.89)
- Dynamic Spatial Propagation Network for Depth Completion (AAAI 2022 · similarity 0.89)
- Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion (CVPR 2025 · similarity 0.89)
- Bilateral Propagation Network for Depth Completion (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
