AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

IncVGGT: Incremental VGGT for Memory-Bounded Long-Range 3D Reconstruction

Keyu Fang, Changchun Zhou, Yuzhe Fu, Hai Helen Li, Yiran Chen

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Block-sparse attention kernels

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 changedWhereMeasuredEffect
apply composite-view registration and top-k cache pruningStreamVGGT · Inference time, 100 framestime (s): 20.09 -> 8.20Improved
apply composite-view registration and top-k cache pruningStreamVGGT · Inference time, 300 framestime (s): 136.72 -> 25.50Improved
apply composite-view registration and top-k cache pruningStreamVGGT · Attention operators, 300 framesoperators (k): 4299.78k -> 126.33kImproved
apply composite-view registration and top-k cache pruningStreamVGGT · Energy, 300 framesenergy (J): 23516.1 -> 811.0Improved
apply composite-view registration and top-k cache pruningStreamVGGT · Reserved memory at 1k framesmemory (GB)Improved
apply composite-view registration and top-k cache pruningStreamVGGT · Video depth: SintelAbs Rel: 0.328 -> 0.341Hurt
apply composite-view registration and top-k cache pruningStreamVGGT · Video depth: BonnAbs Rel: 0.059 -> 0.064Hurt
apply composite-view registration and top-k cache pruningStreamVGGT · Video depth: KITTIAbs Rel: 0.173 -> 0.176Hurt
apply composite-view registration and top-k cache pruningStreamVGGT · Multi-view reconstruction: 7Scenesmedian Acc: 0.0241 -> 0.0266Hurt
apply composite-view registration and top-k cache pruningStreamVGGT · Multi-view reconstruction: NRGBDmedian Acc: 0.0520 -> 0.0516No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy