Research map / 3D vision / 3D generation
Streaming Visual Geometry Transformer
Dong Zhuo, Wenzhao Zheng, Jiahe Guo, Yuqi Wu, Jie Zhou, Jiwen Lu
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 knowledge distillation from VGGT teacher to the causal student (ablation) | StreamVGGT · 7-Scenes (sparse views) | Acc mean: 0.202 -> 0.129 | Improved |
| add knowledge distillation (ablation) | StreamVGGT · NRGBD (sparse views) | Acc mean: 0.189 -> 0.084 | Improved |
| add cached memory tokens at inference (ablation) | StreamVGGT · Online inference at frame 5 | inference time: 850.699 ms -> 88.193 ms | Improved |
| add FlashAttention-2 (ablation) | StreamVGGT · Online inference at frame 5 | peak memory: 5.4 GB -> 2.3 GB | Improved |
| use cached tokens instead of full-sequence causal attention (ablation) | StreamVGGT · ETH3D (streaming) | Overall error / time: time 4.7 s -> 0.07 s; Overall 0.753 -> 0.753 | Improved |
| windowed streaming (50 frames) for long sequences (ablation) | StreamVGGT · 200-frame sequence | inference time: 733.083 ms -> 219.454 ms; Acc mean 0.058 -> 0.054 | Improved |
| K-nearest-frames caching with K=50 instead of K=100 (ablation) | StreamVGGT · 200-frame sequence | Acc mean: 0.054 -> 0.157 | Hurt |
| use causal streaming model instead of offline VGGT | StreamVGGT · 7-Scenes (sparse views) | Acc mean: 0.088 -> 0.129 | Hurt |
| use StreamVGGT instead of CUT3R | streaming reconstruction · ETH3D (10 frames) | Overall: 1.411 -> 0.577 | Improved |
| use StreamVGGT instead of CUT3R | streaming video depth · KITTI video depth | Abs Rel: 0.118 -> 0.173 | Hurt |
| input noise via random masking (ablation) | StreamVGGT · 7-Scenes | Acc mean: 0.034 -> 0.054 (0% -> 25% noise) | Hurt |
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.
- Point3R — Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory (NeurIPS 2025) · better on 2 of 2 shared results
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
- FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry (NeurIPS 2026 · similarity 0.91)
- IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer (NeurIPS 2026 · similarity 0.91)
- TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention (NeurIPS 2026 · similarity 0.89)
- VGGT: Visual Geometry Grounded Transformer (CVPR 2025 · similarity 0.89)
- LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging (CVPR 2026 · similarity 0.88)
- Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer (NeurIPS 2026 · 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.
