Datasets › Tanks and Temples

Tanks and Temples

30 Jul 2017 archive 2025-07-28

We present a benchmark for image-based 3D reconstruction. The benchmark sequences were acquired outside the lab, in realistic conditions. Ground-truth data was captured using an industrial laser scanner. The benchmark includes both outdoor scenes and indoor environments. High-resolution video sequences are provided as input, supporting the development of novel pipelines that take advantage of video input to increase reconstruction fidelity. We report the performance of many image-based 3D reconstruction pipelines on the new benchmark. The results point to exciting challenges and opportunities for future work.

Paper: Arno Knapitsch, Jaesik Park, Qian-Yi Zhou, and Vladlen Koltun. Tanks and temples: Benchmarking large-scale scene reconstruction. In ACM Transactions on Graphics (TOG), 2017.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Point Clouds Tanks and Temples MVSFormer++ Mean F1 (Advanced) 41.70 MVSFormer++: Revealing the Devil in Transformer's... maybelx/mvsformerplusplus 21 Compare
Novel View Synthesis Tanks and Temples TensoRF + NeRFLiX++ PSNR 29.24 From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic... redrock303/NeRFLiX_CPVR2023 10 Compare

Papers archive 2025-07-28

29 shown of 29 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 55. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization 1 1 29 Dec 2024 not harvested
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression 2 1 21 Mar 2024 not harvested
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo 1 1 22 Jan 2024 ran 15 of 19 samples (4 unverified)
Compact 3D Scene Representation via Self-Organizing Gaussian Grids 2 1 19 Dec 2023 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization 1 1 30 Nov 2023 ran 1 of 2 samples (1 unverified)
Compact 3D Gaussian Representation for Radiance Field 1 1 22 Nov 2023 ran 5 of 7 samples (2 unverified; 7 pointer-only for licence)
GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo 1 1 30 Oct 2023 not harvested
When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo 1 1 29 Sep 2023 ran 5 of 13 samples (8 unverified)
3D Gaussian Splatting for Real-Time Radiance Field Rendering 2 1 8 Aug 2023 ran 6 of 10 samples (4 unverified; 10 pointer-only for licence)
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm 1 1 10 Jun 2023 not harvested
Multi-View Stereo Representation Revisit: Region-Aware MVSNet 0 1 26 Apr 2023 not harvested
NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer 1 3 13 Mar 2023 not harvested
GeoMVSNet: Learning Multi-View Stereo With Geometry Perception 1 1 1 Jan 2023 not harvested
Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo 1 1 1 Jan 2023 not harvested
MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth 1 1 4 Aug 2022 ran 12 of 15 samples (3 unverified)
Curvature-guided dynamic scale networks for Multi-view Stereo 1 1 11 Dec 2021 ran 16 of 18 samples (2 unverified; 18 pointer-only for licence)
Generalized Binary Search Network for Highly-Efficient Multi-View Stereo 1 1 4 Dec 2021 not harvested
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions 0 1 29 Nov 2021 not harvested
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields 1 1 23 Nov 2021 not harvested
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network 1 1 9 Aug 2021 ran 4 of 20 samples (16 unverified)
EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo 6 1 1 Jan 2021 not harvested
PatchmatchNet: Learned Multi-View Patchmatch Stereo 1 1 2 Dec 2020 not harvested
Visibility-aware Multi-view Stereo Network 1 1 18 Aug 2020 ran 3 of 14 samples (11 unverified)
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo 1 1 18 Dec 2019 not harvested
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching 4 1 13 Dec 2019 ran 6 of 14 samples (8 unverified)
Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness 1 1 27 Nov 2019 ran 0 of 1 samples (1 unverified)
Multi-Scale Geometric Consistency Guided Multi-View Stereo 0 1 17 Apr 2019 not harvested
MVSNet: Depth Inference for Unstructured Multi-view Stereo 5 1 7 Apr 2018 not harvested
Structure-From-Motion Revisited 1 1 1 Jun 2016 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Creative Commons Attribution-NonCommercial-ShareAlike 3.0

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Tanks and Temples

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections