Benchmarking stereo reconstruction for 3D printable Martian terrain models
Quick Answer
This paper shows that A pipeline for reconstructing 3D printable Martian terrain from NASA Curiosity images shows that while RAFT-Stereo outperforms SGBM on benchmark datasets, its performance on Martian terrain is hindered by weaker edge alignment and higher reprojection errors.
Quick Take
A pipeline for reconstructing 3D printable Martian terrain from NASA Curiosity images shows that while RAFT-Stereo outperforms SGBM on benchmark datasets, its performance on Martian terrain is hindered by weaker edge alignment and higher reprojection errors. Geometry completion methods reveal trade-offs between local fidelity and global connectivity, necessitating stronger domain-specific validation for reliable reconstruction.
Key Points
- RAFT-Stereo reduces disparity MAE from 3.22px to 0.73px compared to SGBM.
- Valid prediction coverage increased from 76.3% to 100.0% using RAFT-Stereo.
- Geometry completion methods show trade-offs in local fidelity and global connectivity.
- Alpha shapes preserve fragmented structures, while Poisson reconstruction adds unsupported surfaces.
- Reliable Martian terrain reconstruction requires stronger domain-specific validation.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 10364v1 Announce Type: new Abstract: Reconstructing printable 3D models from Mars rover imagery is challenging because Martian terrain is low-texture, irregular, and partially observed. We evaluate a pipeline that estimates stereo depth from NASA Curiosity images, completes geometry, and exports watertight OBJ meshes. On Middlebury, RAFT-Stereo outperforms semi-global block matching (SGBM), reducing disparity MAE from 3. 22px to 0. 73px and increasing valid prediction coverage from 76. 3% to 100. 0%.
On Curiosity imagery, however, RAFT's denser disparities show weaker edge alignment and higher photometric reprojection error, suggesting that benchmark accuracy does not directly transfer to Martian terrain reconstruction. Geometry completion demonstrates a tradeoff between local fidelity and global connectivity.
We find that alpha shapes preserve accurate but fragmented structure, Poisson reconstruction produces more coherent meshes but adds unsupported surfaces, and a deterministic diffusion-fill baseline is intermediate but sensitive to stereo quality. Overall, standard stereo and completion methods can produce printable approximations of Martian terrain, but reliable reconstruction requires stronger domain-specific validation.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.