Research map / 3D vision / 3D generation
SAGA: Stochastic Whole-Body Grasping with Contact
Yan Wu, Jiahao Wang, Yan Zhang, Siwei Zhang, Otmar Hilliges, Fisher Yu, Siyu Tang
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 |
|---|---|---|---|
| add multi-task contact label learning plus contact-based optimization (vs single-task with heuristic contact loss) (ablation) | WholeGrasp-VAE · GRAB | contact ratio: 0.81 -> 0.94 | Mixed |
| add GraspPose-Opt contact-aware optimization to sampled grasps (ablation) | WholeGrasp-VAE · GRAB | interpenetration volume: 12.20 -> 0.48 | Improved |
| add collision loss E_colli to E_fit+E_cont^g (ablation) | GraspPose-Opt · GRAB sampled markers | contact ratio: 0.96 -> 0.24 | Mixed |
| add object contact loss E_cont^o on top of collision loss (ablation) | GraspPose-Opt · GRAB sampled markers | contact ratio: 0.24 -> 0.94 | Improved |
| use marker representation plus optimization instead of direct SMPL-X parameter regression | WholeGrasp-VAE · GRAB | APD: 0.33 -> 2.92 | Improved |
| use generative end-to-end trajectory and local motion infilling instead of Route+PoseNet | MotionFill-VAE · Traj + local motion infilling | ADE: 0.219 -> 0.083 | Improved |
| use generative local motion infilling instead of LEMO | LocalMotionFill-CVAE · Local motion infilling | ADE: 0.083 -> 0.079 | Improved |
| use generative local infilling instead of LEMO | LocalMotionFill-CVAE · Local motion infilling | foot skating: 0.152 -> 0.137 | Improved |
Later papers that compared with this method
13 later accepted papers report SAGA as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.
- Semantic Foam: Unifying Spatial and Semantic Scene Decomposition (CVPR 2026 · better on 4 of 6 shared results)
- Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentation (AAAI 2026 · better on 4 of 4 shared results)
- Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field (IJCV 2026 · better on 4 of 4 shared results)
- LEGO: Leveled Language Gaussian Splatting (ECCV 2026 · better on 3 of 3 shared results)
- AG2aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing (ICCV 2025 · better on 6 of 8 shared results)
- WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images (ICCV 2025 · better on 4 of 4 shared results)
- iSegMan: Interactive Segment-and-Manipulate 3D Gaussians (CVPR 2025 · better on 2 of 2 shared results)
- LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes (ICCV 2025 · better on 1 of 2 shared results)
5 more not listed.
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
- DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model (AAAI 2025 · similarity 0.91)
- CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects (NeurIPS 2025 · similarity 0.88)
- LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion. (CVPR 2025 · similarity 0.88)
- Single-View Scene Point Cloud Human Grasp Generation (CVPR 2024 · similarity 0.88)
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (CVPR 2024 · similarity 0.87)
- RAGG: Retrieval-Augmented Grasp Generation Model (AAAI 2025 · 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.
