# VK

Source: [VK](<https://www.sota2.com/research/dataset/vk>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Benchmarks

Page 1 of 1. This is an index page, not the full collection.

- [Multi-modal Visual Reasoning on VKnowU](<https://www.sota2.com/research/sota/multi-modal-visual-reasoning-on-vknowu.md>): Multi-modal Visual Reasoning; VKnowU.

- [Knowledge Editing on EVK-Bench](<https://www.sota2.com/research/sota/knowledge-editing-on-evk-bench.md>): Knowledge Editing; EVK-Bench.

- [Semantic Segmentation on vKITTI 2](<https://www.sota2.com/research/sota/semantic-segmentation-on-vkitti-2.md>): Semantic Segmentation; vKITTI 2.

- [3D Reconstruction on VKITTI 2 (ATE)](<https://www.sota2.com/research/sota/3d-reconstruction-on-vkitti-2-ate.md>): 3D Reconstruction; VKITTI 2.

- [Semantic Segmentation on Cityscapes 8 classes (VKITTI2 context)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-8-classes-vkitti2-context.md>): Semantic Segmentation; VKITTI2 -\> Cityscapes 8 classes.

- [Depth Completion on Outdoor sequence KITTI → Waymo → VKITTI](<https://www.sota2.com/research/sota/depth-completion-on-outdoor-sequence-kitti-waymo-vkitti.md>): Depth Completion; Outdoor sequence KITTI → Waymo → VKITTI.

- [Depth Completion on VKITTI FOG](<https://www.sota2.com/research/sota/depth-completion-on-vkitti-fog.md>): Depth Completion; VKITTI FOG.

- [Disparity Estimation on Vkitti 2](<https://www.sota2.com/research/sota/disparity-estimation-on-vkitti-2.md>): Disparity Estimation; Vkitti 2.

- [Depth Completion on Waymo -\> VKITTI-FOG (test)](<https://www.sota2.com/research/sota/depth-completion-on-waymo-vkitti-fog-test.md>): Depth completion; Waymo → VKITTI-FOG (test).

- [Multi-Task Learning on VKITTI 2 (test)](<https://www.sota2.com/research/sota/multi-task-learning-on-vkitti-2-test.md>): Multi-Task Learning; VKITTI 2 (test).

- [Novel View Synthesis on VKITTI 2 (25% train views)](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti-2-25-percent-train-views.md>): Novel View Synthesis; VKITTI 2 (25% train views).

- [Video Understanding on VKnowU](<https://www.sota2.com/research/sota/video-understanding-on-vknowu.md>): Video Understanding; VKnowU.

- [3D Reconstruction on VKITTI2](<https://www.sota2.com/research/sota/3d-reconstruction-on-vkitti2.md>): 3D reconstruction; VKITTI2.

- [Depth Estimation on VKITTI2 11 (test)](<https://www.sota2.com/research/sota/depth-estimation-on-vkitti2-11-test.md>): Depth Estimation; VKITTI2 11 (test).

- [Scene Flow Estimation on VKITTI2 11 (test)](<https://www.sota2.com/research/sota/scene-flow-estimation-on-vkitti2-11-test.md>): Scene Flow Estimation; VKITTI2 11 (test).

- [Generative Retrieval on VK-LSVD (block 10)](<https://www.sota2.com/research/sota/generative-retrieval-on-vk-lsvd-block-10.md>): Generative Retrieval; VK-LSVD (block 10).

- [Camera Pose Estimation on vKITTI](<https://www.sota2.com/research/sota/camera-pose-estimation-on-vkitti.md>): Camera pose estimation; vKITTI.

- [Depth Estimation on VKITTI2 Real](<https://www.sota2.com/research/sota/depth-estimation-on-vkitti2-real.md>): Depth Estimation; VKITTI2 Real.

- [Scene Flow Estimation on VKITTI 2 (Real)](<https://www.sota2.com/research/sota/scene-flow-estimation-on-vkitti-2-real.md>): Scene Flow Estimation; VKITTI 2 (Real).

- [Depth Estimation on VKITT 2 (test)](<https://www.sota2.com/research/sota/depth-estimation-on-vkitt-2-test.md>): Depth Estimation; VKITT 2 (test).

- [Surface Normal Estimation on VKITT2 (test)](<https://www.sota2.com/research/sota/surface-normal-estimation-on-vkitt2-test.md>): Surface Normal Estimation; VKITT2 (test).

- [Semantic Segmentation on VKITT 2 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-vkitt-2-test.md>): Semantic Segmentation; VKITT 2 (test).

- [World-centric motion reconstruction on VKITTI 2](<https://www.sota2.com/research/sota/world-centric-motion-reconstruction-on-vkitti-2.md>): World-centric motion reconstruction; VKITTI 2.

- [World-centric geometry reconstruction on VKITTI2](<https://www.sota2.com/research/sota/world-centric-geometry-reconstruction-on-vkitti2.md>): World-centric geometry reconstruction; VKITTI2.

- [Depth Estimation on VKITTI2 -\> Cityscapes (8 classes)](<https://www.sota2.com/research/sota/depth-estimation-on-vkitti2-cityscapes-8-classes.md>): Depth Estimation; VKITTI2 -\> Cityscapes (8 classes).

- [Novel View Synthesis on VKITTI2 25% (test)](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti2-25-percent-test.md>): Novel View Synthesis; VKITTI2 25% (test).

- [Novel View Synthesis on VKITTI2 50% (test)](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti2-50-percent-test.md>): Novel View Synthesis; VKITTI2 50% (test).

- [Novel View Synthesis on VKITTI2 75% (test)](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti2-75-percent-test.md>): Novel View Synthesis; VKITTI2 75% (test).

- [Instance Segmentation on vKITTI2](<https://www.sota2.com/research/sota/instance-segmentation-on-vkitti2.md>): Instance Segmentation; vKITTI2.

- [Classification on chess\_krvkp UCI KEEL (test)](<https://www.sota2.com/research/sota/classification-on-chess_krvkp-uci-keel-test.md>): Classification; chess\_krvkp UCI KEEL (test).

- [Dense Scene Flow Estimation on VKITTI Scene Flow 2 (held-out scenes)](<https://www.sota2.com/research/sota/dense-scene-flow-estimation-on-vkitti-scene-flow-2-held-out-scenes.md>): Dense Scene Flow Estimation; VKITTI Scene Flow 2 (held-out scenes).

- [Dense Scene Flow Estimation on VKITTI-2 Dynamic Points (held-out scenes)](<https://www.sota2.com/research/sota/dense-scene-flow-estimation-on-vkitti-2-dynamic-points-held-out-scenes.md>): Dense Scene Flow Estimation; VKITTI-2 Dynamic Points (held-out scenes).

- [Stereo Camera Calibration on Prophesee EVK4](<https://www.sota2.com/research/sota/stereo-camera-calibration-on-prophesee-evk4.md>): Stereo Camera Calibration; Prophesee EVK4.

- [Novel View Synthesis on VKITTI2 50% views (train)](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti2-50-percent-views-train.md>): Novel View Synthesis; VKITTI2 50% views (train).

- [Novel View Synthesis on VKITTI2 (75% train views)](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti2-75-percent-train-views.md>): Novel View Synthesis; VKITTI2 (75% train views).

- [Monocular Depth Estimation on Unconstrained Scenes Composite (NYU, KITTI, iBims-1, vKITTI2)](<https://www.sota2.com/research/sota/monocular-depth-estimation-on-unconstrained-scenes-composite-nyu-kitti-ibims-1-vkitti2.md>): Monocular Depth Estimation; Unconstrained Scenes Composite NYU, KITTI, iBims-1, vKITTI2.

- [Monocular Depth Estimation on vKITTI 2](<https://www.sota2.com/research/sota/monocular-depth-estimation-on-vkitti-2.md>): Monocular Depth Estimation; vKITTI 2.

- [Multi-Task Learning Performance on VKITT2, Hypersim, and FlyingThings3D (test)](<https://www.sota2.com/research/sota/multi-task-learning-performance-on-vkitt2-hypersim-and-flyingthings3d-test.md>): Multi-Task Learning Performance; VKITT2, Hypersim, and FlyingThings3D (test).

- [Scene Flow Estimation on VKITT2 (test)](<https://www.sota2.com/research/sota/scene-flow-estimation-on-vkitt2-test.md>): Scene Flow Estimation; VKITT2 (test).

- [Optical Flow Estimation on VKITT2 (test)](<https://www.sota2.com/research/sota/optical-flow-estimation-on-vkitt2-test.md>): Optical Flow Estimation; VKITT2 (test).

- [Sequential Recommendation on VK-LSVD (test)](<https://www.sota2.com/research/sota/sequential-recommendation-on-vk-lsvd-test.md>): Sequential Recommendation; VK-LSVD (test).

- [Novel View Synthesis on VKITTI2](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti2.md>): Novel View Synthesis; VKITTI2.

- [Stereo Matching on Virtual KITTI (VKITTI) (val)](<https://www.sota2.com/research/sota/stereo-matching-on-virtual-kitti-vkitti-val.md>): Stereo Matching; Virtual KITTI (VKITTI) (val).

- [Transferability Prediction on vKITTI 2 (test)](<https://www.sota2.com/research/sota/transferability-prediction-on-vkitti-2-test.md>): Transferability Prediction; vKITTI 2 (test).

- [Node Classification on VK\_class](<https://www.sota2.com/research/sota/node-classification-on-vk_class.md>): Node Classification; VK\_class.

- [Surface Normal Estimation on VKitti](<https://www.sota2.com/research/sota/surface-normal-estimation-on-vkitti.md>): Surface normal estimation; VKitti.

- [LLM-as-judge head-to-head comparison on VK State](<https://www.sota2.com/research/sota/llm-as-judge-head-to-head-comparison-on-vk-state.md>): LLM-as-judge head-to-head comparison; VK State.

- [Multi-Task Learning on VKITTI2 -\> Cityscapes 8 classes](<https://www.sota2.com/research/sota/multi-task-learning-on-vkitti2-cityscapes-8-classes.md>): Multi-Task Learning; VKITTI2 -\> Cityscapes 8 classes.

- [Novel View Synthesis on vKITTI Scene06 (test)](<https://www.sota2.com/research/sota/novel-view-synthesis-on-vkitti-scene06-test.md>): Novel View Synthesis; vKITTI Scene06 (test).

- [Multi-Object Detection on vKITTI](<https://www.sota2.com/research/sota/multi-object-detection-on-vkitti.md>): Multi-Object Detection; vKITTI.

- [Multi-Object Tracking on vKITTI](<https://www.sota2.com/research/sota/multi-object-tracking-on-vkitti.md>): Multi-Object Tracking; vKITTI.

- [3D Semantic Segmentation on vKITTI (6-fold val)](<https://www.sota2.com/research/sota/3d-semantic-segmentation-on-vkitti-6-fold-val.md>): 3D Semantic Segmentation; vKITTI (6-fold val).

- [Auto-focusing on EVK4](<https://www.sota2.com/research/sota/auto-focusing-on-evk4.md>): Auto-focusing; EVK4.

- [Image Recombination on VKITTI](<https://www.sota2.com/research/sota/image-recombination-on-vkitti.md>): Image Recombination; VKITTI.