AI Paper Atlas

Research map / 3D vision / Depth and stereo

Sky2Ground: A Benchmark for Site Modeling under Varying Altitude

Zengyan Wang, Sirshapan Mitra, Rajat Modi, Hui Lim, Yogesh Rawat

CVPR 2026 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 1 citations (OpenAlex)

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
add Masked-Satellite Attention (MSA) (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 53.8 -> 62.7Improved
add Progressive-View Sampling (P-VS) (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 53.8 -> 61.1Improved
add Curriculum-Aware Camera Sampling (CA-CS) (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 53.8 -> 54.3Improved
add CA-CS on top of MSA (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 62.7 -> 63.8Improved
add P-VS on top of MSA (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 62.7 -> 64.9Improved
add CA-CS to MSA + P-VS (full model) (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 64.9 -> 65.1Improved
also feed satellite images to the GAS encoder, not only Sat-Encoder (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 53.1 -> 53.8Improved
replace additive satellite-token fusion with cross-attention (ablation)SkyNet · Sky2Ground G+Savg RRA/RTA: 65.1 -> 59.7Hurt
add 24 extra layers to VGGT (parameter-matched) (ablation)VGGT fine-tuned · Sky2Ground G+Savg RRA/RTA: 47.8 -> 50.4Mixed
fine-tune VGGT on Sky2Ground including satelliteVGGT · Sky2Ground GASavg RRA: 73.6 -> 55.4Hurt
fine-tune Dust3r on ground-aerial dataDust3r · Sky2Ground GASavg RRA: 58.9 -> 64.1Improved
fine-tune Mast3r on ground-aerial dataMast3r · Sky2Ground GASavg RRA: 53.2 -> 67.6Improved

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.

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

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